This application claims priority from U.S. Provisional Patent Application Ser. No. 62/148,604, entitled “PARSIMONIOUS CONTINUOUS-SPACE PHRASE REPRESENTATIONS FOR NATURAL LANGUAGE PROCESSING,” filed Apr. 16, 2015, the content of which is hereby incorporated by reference in its entirety.
1. Field
The present disclosure relates generally to speech recognition, and more specifically to techniques for providing continuous-space phrase representations.
2. Description of Related Art
Current speech recognition systems make use of word embeddings to perform various natural language processing tasks. Relatively elementary word embeddings typically rely on 1-of-N encoding, where each word in an underlying vocabulary of size N is represented by a respective vector of dimension N. On the other hand, more sophisticated word embeddings map words of an underlying vocabulary into vectors of a lower-dimensional space, allowing for each vector to include local and/or global context of the word corresponding to the vector.
Such word embeddings, however, are not without weaknesses. For example, embeddings relying on local context poorly utilize corpus statistical information, and embeddings relying on global context present challenges when used to parse particular semantic mechanisms, such as analogies. Moreover, in many cases homonymous and/or polysemous words must be disambiguated prior to embedding for proper operation.
Systems and processes for natural language processing are provided. In accordance with one example, a method includes, at a first electronic device with one or more processors and memory, receiving a plurality of words, mapping each of the plurality of words to a word representation, and associating the mapped words to provide a plurality of phrases. In some examples, each of the plurality of phrases has a representation of a first type. The method further includes encoding each of the plurality of phrases to provide a respective plurality of encoded phrases. In some examples, each of the plurality of encoded phrases has a representation of a second type different than the first type. The method further includes determining a value of each of the plurality of encoded phrases and identifying one or more phrases of the plurality of encoded phrases having a value exceeding a threshold.
For a better understanding of the various described embodiments, reference should be made to the Description of Embodiments below, in conjunction with the following drawings in which like reference numerals refer to corresponding parts throughout the figures.
FIG. 1A is a block diagram illustrating a portable multifunction device with a touch-sensitive display in accordance with some examples.
FIG. 1B is a block diagram illustrating exemplary components for event handling in accordance with some embodiments.
FIG. 2 illustrates a portable multifunction device having a touch screen in accordance with some embodiments.
FIG. 3 is a block diagram of an exemplary multifunction device with a display and a touch-sensitive surface in accordance with some embodiments.
FIGS. 4A and 4B illustrate an exemplary user interface for a menu of applications on a portable multifunction device in accordance with some embodiments.
FIG. 5 illustrates an exemplary schematic block diagram of a phrase embedding system in accordance with some embodiments.
FIG. 6 illustrates an exemplary network for embedding words in accordance with some embodiments.
FIG. 7 illustrates an exemplary encoder in accordance with some embodiments.
FIG. 8 illustrates a flow diagram of an exemplary process for embedding phrases in accordance with some embodiments.
FIG. 9 illustrates a functional block diagram of an electronic device in accordance with some embodiments.
In the following description of the disclosure and embodiments, reference is made to the accompanying drawings in which it is shown by way of illustration of specific embodiments that can be practiced. It is to be understood that other embodiments and examples can be practiced and changes can be made without departing from the scope of the disclosure.
Techniques for providing continuous-space phrase representations are desirable. As described herein, these techniques provide complex and discriminatory phrase embeddings that include sematic, syntactic and/or pragmatic information. Such embeddings are useful in a number of natural language processing applications including but not limited to information retrieval, document classification, questing answering and connectionist language modeling.
Although the following description uses terms first, second, etc. to describe various elements, these elements should not be limited by the terms. These terms are only used to distinguish one element from another. For example, a first contact could be termed a second contact, and, similarly, a second contact could be termed a first contact, without departing from the scope of the present invention. The first contact and the second contact are both contacts, but they are not the same contact.
The terminology used in the description of the various described embodiments herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used in the description of the various described embodiments and the appended claims, the singular forms “a”, “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term “if” may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” may be construed to mean “upon determining” or “in response to determining” or “upon detecting [the stated condition or event]” or “in response to detecting [the stated condition or event],” depending on the context.
Embodiments of electronic devices, systems for providing embedded phrases on such devices, and associated processes for using such devices are described. In some embodiments, the device is a portable communications device, such as a mobile telephone, that also contains other functions, such as PDA and/or music player functions. Exemplary embodiments of portable multifunction devices include, without limitation, the iPhone®, iPod Touch®, and iPad® devices from Apple Inc. of Cupertino, Calif. Other portable devices, such as laptops or tablet computers with touch-sensitive surfaces (e.g., touch screen displays and/or touch pads), may also be used. Exemplary embodiments of laptop and tablet computers include, without limitation, the iPad® and MacBook® devices from Apple Inc. of Cupertino, Calif. It should also be understood that, in some embodiments, the device is not a portable communications device, but is a desktop computer. Exemplary embodiments of desktop computers include, without limitation, the Mac Pro® from Apple Inc. of Cupertino, Calif.
In the discussion that follows, an electronic device that includes a display and a touch-sensitive surface is described. It should be understood, however, that the electronic device optionally includes one or more other physical user-interface devices, such as button(s), a physical keyboard, a mouse, and/or a joystick.
The device may support a variety of applications, such as one or more of the following: a drawing application, a presentation application, a word processing application, a website creation application, a disk authoring application, a spreadsheet application, a gaming application, a telephone application, a video conferencing application, an e-mail application, an instant messaging application, a workout support application, a photo management application, a digital camera application, a digital video camera application, a web browsing application, a digital music player application, and/or a digital video player application.
The various applications that are executed on the device optionally use at least one common physical user-interface device, such as the touch-sensitive surface. One or more functions of the touch-sensitive surface as well as corresponding information displayed on the device are, optionally, adjusted and/or varied from one application to the next and/or within a respective application. In this way, a common physical architecture (such as the touch-sensitive surface) of the device optionally supports the variety of applications with user interfaces that are intuitive and transparent to the user.
FIGS. 1A and 1B are block diagrams illustrating exemplary portable multifunction device 100 with touch-sensitive displays 112 in accordance with some embodiments. Touch-sensitive display 112 is sometimes called a “touch screen” for convenience. Device 100 may include memory 102. Device 100 may include memory controller 122, one or more processing units (CPU's) 120, peripherals interface 118, RF circuitry 108, audio circuitry 110, speaker 111, microphone 113, input/output (I/O) subsystem 106, other input or control devices 116, and external port 124. Device 100 may include one or more optical sensors 164. Bus/signal lines 103 may allow these components to communicate with one another. Device 100 is one example of an electronic device that could be used to perform the techniques described herein. Specific implementations involving device 100 may have more or fewer components than shown, may combine two or more components, or may have a different configuration or arrangement of the components. The various components shown in FIGS. 1A and 1B may be implemented in hardware, software, or a combination of both. The components also can be implemented using one or more signal processing and/or application specific integrated circuits.
Memory 102 may include one or more computer readable storage mediums. The computer readable storage mediums may be tangible and non-transitory. Memory 102 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. Memory controller 122 may control access to memory 102 by other components of device 100.
Peripherals interface 118 can be used to couple input and output peripherals of the device to CPU 120 and memory 102. The one or more processors 120 run or execute various software programs and/or sets of instructions stored in memory 102 to perform various functions for device 100 and to process data. In some embodiments, peripherals interface 118, CPU 120, and memory controller 122 may be implemented on a single chip, such as chip 104. In some other embodiments, they may be implemented on separate chips.
RF (radio frequency) circuitry 108 receives and sends RF signals, also called electromagnetic signals. RF circuitry 108 converts electrical signals to/from electromagnetic signals and communicates with communications networks and other communications devices via the electromagnetic signals. RF circuitry 108 may include well-known circuitry for performing these functions, including but not limited to an antenna system, an RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a CODEC chipset, a subscriber identity module (SIM) card, memory, and so forth. RF circuitry 108 may communicate with networks, such as the Internet, also referred to as the World Wide Web (WWW), an intranet and/or a wireless network, such as a cellular telephone network, a wireless local area network (LAN) and/or a metropolitan area network (MAN), and other devices by wireless communication. The wireless communication may use any of a plurality of communications standards, protocols and technologies, including but not limited to Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), high-speed downlink packet access (HSDPA), wideband code division multiple access (W-CDMA), code division multiple access (CDMA), time division multiple access (TDMA), Bluetooth, Bluetooth Low Energy (BTLE), Wireless Fidelity (Wi-Fi) (e.g., IEEE 502.11a, IEEE 502.11b, IEEE 802.11g and/or IEEE 802.11n), voice over Internet Protocol (VoIP), Wi-MAX, a protocol for e-mail (e.g., Internet message access protocol (IMAP) and/or post office protocol (POP)), instant messaging (e.g., extensible messaging and presence protocol (XMPP), Session Initiation Protocol for Instant Messaging and Presence Leveraging Extensions (SIMPLE), Instant Messaging and Presence Service (IMPS)), and/or Short Message Service (SMS), or any other suitable communication protocol, including communication protocols not yet developed as of the filing date of this document.
Audio circuitry 110, speaker 111, and microphone 113 provide an audio interface between a user and device 100. Audio circuitry 110 receives audio data from peripherals interface 118, converts the audio data to an electrical signal, and transmits the electrical signal to speaker 111. Speaker 111 converts the electrical signal to human-audible sound waves. Audio circuitry 110 also receives electrical signals converted by microphone 113 from sound waves. Audio circuitry 110 converts the electrical signal to audio data and transmits the audio data to peripherals interface 118 for processing. Audio data may be retrieved from and/or transmitted to memory 102 and/or RF circuitry 108 by peripherals interface 118. In some embodiments, audio circuitry 110 also includes a headset jack (e.g., 212, FIG. 2). The headset jack provides an interface between audio circuitry 110 and removable audio input/output peripherals, such as output-only headphones or a headset with both output (e.g., a headphone for one or both ears) and input (e.g., a microphone).
I/O subsystem 106 couples input/output peripherals on device 100, such as touch screen 112 and other input control devices 116, to peripherals interface 118. I/O subsystem 106 may include display controller 156 and one or more input controllers 160 for other input or control devices. The one or more input controllers 160 receive/send electrical signals from/to other input or control devices 116. The other input control devices 116 may include physical buttons (e.g., push buttons, rocker buttons, etc.), dials, slider switches, joysticks, click wheels, and so forth. In some alternate embodiments, input controller(s) 160 may be coupled to any (or none) of the following: a keyboard, infrared port, USB port, and a pointer device such as a mouse. The one or more buttons (e.g., 208, FIG. 2) may include an up/down button for volume control of speaker 111 and/or microphone 113. The one or more buttons may include a push button (e.g., 206, FIG. 2). A quick press of the push button may disengage a lock of touch screen 112 or begin a process that uses gestures on the touch screen to unlock the device, as described in U.S. patent application Ser. No. 11/322,549, “Unlocking a Device by Performing Gestures on an Unlock Image,” filed Dec. 23, 2005, U.S. Pat. No. 7,657,849, which is hereby incorporated by reference in its entirety. A longer press of the push button (e.g., 206) may turn power to device 100 on or off. The user may be able to customize a functionality of one or more of the buttons. Touch screen 112 is used to implement virtual or soft buttons and one or more soft keyboards.
Touch-sensitive display 112 provides an input interface and an output interface between the device and a user. Display controller 156 receives and/or sends electrical signals from/to touch screen 112. Touch screen 112 displays visual output to the user. The visual output may include graphics, text, icons, video, and any combination thereof (collectively termed “graphics”). In some embodiments, some or all of the visual output may correspond to user-interface objects.
Touch screen 112 has a touch-sensitive surface, sensor or set of sensors that accepts input from the user based on haptic and/or tactile contact. Touch screen 112 and display controller 156 (along with any associated modules and/or sets of instructions in memory 102) detect contact (and any movement or breaking of the contact) on touch screen 112 and converts the detected contact into interaction with user-interface objects (e.g., one or more soft keys, icons, web-pages or images) that are displayed on touch screen 112. In an exemplary embodiment, a point of contact between touch screen 112 and the user corresponds to a finger of the user.
Touch screen 112 may use LCD (liquid crystal display) technology, LPD (light emitting polymer display) technology, or LED (light emitting diode) technology, although other display technologies may be used in other embodiments. Touch screen 112 and display controller 156 may detect contact and any movement or breaking thereof using any of a plurality of touch sensing technologies now known or later developed, including but not limited to capacitive, resistive, infrared, and surface acoustic wave technologies, as well as other proximity sensor arrays or other elements for determining one or more points of contact with touch screen 112. In an exemplary embodiment, projected mutual capacitance sensing technology is used, such as that found in the iPhone® and iPod Touch® from Apple Inc. of Cupertino, Calif.
A touch-sensitive display in some embodiments of touch screen 112 may be analogous to the multi-touch sensitive touchpads described in the following U.S. Pat. No. 6,323,846 (Westerman et al.), U.S. Pat. No. 6,570,557 (Westerman et al.), and/or U.S. Pat. No. 6,677,932 (Westerman), and/or U.S. Patent Publication 2002/0015024A1, each of which is hereby incorporated by reference in its entirety. However, touch screen 112 displays visual output from device 100, whereas touch sensitive touchpads do not provide visual output.
A touch-sensitive display in some embodiments of touch screen 112 may be as described in the following applications: (1) U.S. patent application Ser. No. 11/381,313, “Multipoint Touch Surface Controller,” filed May 2, 2006; (2) U.S. patent application Ser. No. 10/840,862, “Multipoint Touchscreen,” filed May 6, 2004; (3) U.S. patent application Ser. No. 10/903,964, “Gestures For Touch Sensitive Input Devices,” filed Jul. 30, 2004; (4) U.S. patent application Ser. No. 11/048,264, “Gestures For Touch Sensitive Input Devices,” filed Jan. 31, 2005; (5) U.S. patent application Ser. No. 11/038,590, “Mode-Based Graphical User Interfaces For Touch Sensitive Input Devices,” filed Jan. 18, 2005; (6) U.S. patent application Ser. No. 11/228,758, “Virtual Input Device Placement On A Touch Screen User Interface,” filed Sep. 16, 2005; (7) U.S. patent application Ser. No. 11/228,700, “Operation Of A Computer With A Touch Screen Interface,” filed Sep. 16, 2005; (8) U.S. patent application Ser. No. 11/228,737, “Activating Virtual Keys Of A Touch-Screen Virtual Keyboard,” filed Sep. 16, 2005; and (9) U.S. patent application Ser. No. 11/367,749, “Multi-Functional Hand-Held Device,” filed Mar. 3, 2006. All of these applications are incorporated by reference herein in their entirety.
Touch screen 112 may have a video resolution in excess of 100 dpi. In some embodiments, the touch screen has a video resolution of approximately 160 dpi. The user may make contact with touch screen 112 using any suitable object or appendage, such as a stylus, a finger, and so forth. In some embodiments, the user interface is designed to work primarily with finger-based contacts and gestures, which can be less precise than stylus-based input due to the larger area of contact of a finger on the touch screen. In some embodiments, the device translates the rough finger-based input into a precise pointer/cursor position or command for performing the actions desired by the user.
In some embodiments, in addition to the touch screen, device 100 may include a touchpad (not shown) for activating or deactivating particular functions. In some embodiments, the touchpad is a touch-sensitive area of the device that, unlike the touch screen, does not display visual output. The touchpad may be a touch-sensitive surface that is separate from touch screen 112 or an extension of the touch-sensitive surface formed by the touch screen.
Device 100 also includes power system 162 for powering the various components. Power system 162 may include a power management system, one or more power sources (e.g., battery, alternating current (AC)), a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator (e.g., a light-emitting diode (LED)) and any other components associated with the generation, management and distribution of power in portable devices.
Device 100 may also include one or more optical sensors 164. FIGS. 1A and 1B show an optical sensor coupled to optical sensor controller 158 in I/O subsystem 106. Optical sensor 164 may include charge-coupled device (CCD) or complementary metal-oxide semiconductor (CMOS) phototransistors. Optical sensor 164 receives light from the environment, projected through one or more lens, and converts the light to data representing an image. In conjunction with imaging module 143 (also called a camera module), optical sensor 164 may capture still images or video. In some embodiments, an optical sensor is located on the back of device 100, opposite touch screen display 112 on the front of the device, so that the touch screen display may be used as a viewfinder for still and/or video image acquisition. In some embodiments, an optical sensor is located on the front of the device so that the user's image may be obtained for videoconferencing while the user views the other video conference participants on the touch screen display. In some embodiments, the position of optical sensor 164 can be changed by the user (e.g., by rotating the lens and the sensor in the device housing) so that a single optical sensor 164 may be used along with the touch screen display for both video conferencing and still and/or video image acquisition.
Device 100 may also include one or more proximity sensors 166. FIGS. 1A and 1B show proximity sensor 166 coupled to peripherals interface 118. Alternately, proximity sensor 166 may be coupled to input controller 160 in I/O subsystem 106. Proximity sensor 166 may perform as described in U.S. patent application Ser. No. 11/241,839, “Proximity Detector In Handheld Device”; Ser. No. 11/240,788, “Proximity Detector In Handheld Device”; Ser. No. 11/620,702, “Using Ambient Light Sensor To Augment Proximity Sensor Output”; Ser. No. 11/586,862, “Automated Response To And Sensing Of User Activity In Portable Devices”; and Ser. No. 11/638,251, “Methods And Systems For Automatic Configuration Of Peripherals,” which are hereby incorporated by reference in their entirety. In some embodiments, the proximity sensor turns off and disables touch screen 112 when the multifunction device is placed near the user's ear (e.g., when the user is making a phone call).
Device 100 optionally also includes one or more tactile output generators 167. FIG. 1A shows a tactile output generator coupled to haptic feedback controller 161 in I/O subsystem 106. Tactile output generator 167 optionally includes one or more electroacoustic devices such as speakers or other audio components and/or electromechanical devices that convert energy into linear motion such as a motor, solenoid, electroactive polymer, piezoelectric actuator, electrostatic actuator, or other tactile output generating component (e.g., a component that converts electrical signals into tactile outputs on the device). Contact intensity sensor 165 receives tactile feedback generation instructions from haptic feedback module 133 and generates tactile outputs on device 100 that are capable of being sensed by a user of device 100. In some embodiments, at least one tactile output generator is collocated with, or proximate to, a touch-sensitive surface (e.g., touch-sensitive display system 112) and, optionally, generates a tactile output by moving the touch-sensitive surface vertically (e.g., in/out of a surface of device 100) or laterally (e.g., back and forth in the same plane as a surface of device 100). In some embodiments, at least one tactile output generator sensor is located on the back of device 100, opposite touch screen display 112, which is located on the front of device 100.
Device 100 may also include one or more accelerometers 168. FIGS. 1A and 1B show accelerometer 168 coupled to peripherals interface 118. Alternately, accelerometer 168 may be coupled to an input controller 160 in I/O subsystem 106. Accelerometer 168 may perform as described in U.S. Patent Publication No. 20050190059, “Acceleration-based Theft Detection System for Portable Electronic Devices,” and U.S. Patent Publication No. 20060017692, “Methods And Apparatuses For Operating A Portable Device Based On An Accelerometer,” both of which are which are incorporated by reference herein in their entirety. In some embodiments, information is displayed on the touch screen display in a portrait view or a landscape view based on an analysis of data received from the one or more accelerometers. Device 100 optionally includes, in addition to accelerometer(s) 168, a magnetometer (not shown) and a GPS (or GLONASS or other global navigation system) receiver (not shown) for obtaining information concerning the location and orientation (e.g., portrait or landscape) of device 100.
In some embodiments, the software components stored in memory 102 include operating system 126, communication module (or set of instructions) 128, contact/motion module (or set of instructions) 130, graphics module (or set of instructions) 132, text input module (or set of instructions) 134, Global Positioning System (GPS) module (or set of instructions) 135, and applications (or sets of instructions) 136. Furthermore, in some embodiments memory 102 stores device/global internal state 157, as shown in FIGS. 1A, 1B and 3. Device/global internal state 157 includes one or more of: active application state, indicating which applications, if any, are currently active; display state, indicating what applications, views or other information occupy various regions of touch screen display 112; sensor state, including information obtained from the device's various sensors and input control devices 116; and location information concerning the device's location and/or attitude.
Operating system 126 (e.g., Darwin, RTXC, LINUX, UNIX, OS X, iOS, WINDOWS, or an embedded operating system such as VxWorks) includes various software components and/or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.) and facilitates communication between various hardware and software components.
Communication module 128 facilitates communication with other devices over one or more external ports 124 and also includes various software components for handling data received by RF circuitry 108 and/or external port 124. External port 124 (e.g., Universal Serial Bus (USB), FIREWIRE, etc.) is adapted for coupling directly to other devices or indirectly over a network (e.g., the Internet, wireless LAN, etc.). In some embodiments, the external port is a multi-pin connector that is the same as, or similar to and/or compatible with the 5-pin and/or 30-pin connectors used on devices made by Apple Inc.
Contact/motion module 130 may detect contact with touch screen 112 (in conjunction with display controller 156) and other touch sensitive devices (e.g., a touchpad or physical click wheel). Contact/motion module 130 includes various software components for performing various operations related to detection of contact, such as determining if contact has occurred (e.g., detecting a finger-down event), determining if there is movement of the contact and tracking the movement across the touch-sensitive surface (e.g., detecting one or more finger-dragging events), and determining if the contact has ceased (e.g., detecting a finger-up event or a break in contact). Contact/motion module 130 receives contact data from the touch-sensitive surface. Determining movement of the point of contact, which is represented by a series of contact data, may include determining speed (magnitude), velocity (magnitude and direction), and/or an acceleration (a change in magnitude and/or direction) of the point of contact. These operations may be applied to single contacts (e.g., one finger contacts) or to multiple simultaneous contacts (e.g., “multitouch”/multiple finger contacts). In some embodiments, contact/motion module 130 and display controller 156 detects contact on a touchpad. In some embodiments, contact/motion module 130 and controller 160 detects contact on a click wheel.
Contact/motion module 130 may detect a gesture input by a user. Different gestures on the touch-sensitive surface have different contact patterns. Thus, a gesture may be detected by detecting a particular contact pattern. For example, detecting a finger tap gesture includes detecting a finger-down event followed by detecting a finger-up (lift off) event at the same position (or substantially the same position) as the finger-down event (e.g., at the position of an icon). As another example, detecting a finger swipe gesture on the touch-sensitive surface includes detecting a finger-down event followed by detecting one or more finger-dragging events, and subsequently followed by detecting a finger-up (lift off) event.
Graphics module 132 includes various known software components for rendering and displaying graphics on touch screen 112 or other display, including components for changing the intensity of graphics that are displayed. As used herein, the term “graphics” includes any object that can be displayed to a user, including without limitation text, web-pages, icons (such as user-interface objects including soft keys), digital images, videos, animations and the like. In some embodiments, graphics module 132 stores data representing graphics to be used. Each graphic may be assigned a corresponding code. Graphics module 132 receives, from applications etc., one or more codes specifying graphics to be displayed along with, if necessary, coordinate data and other graphic property data, and then generates screen image data to output to display controller 156.
Haptic feedback module 133 includes various software components for generating instructions used by tactile output generator(s) 167 to produce tactile outputs at one or more locations on device 100 in response to user interactions with device 100.
Text input module 134, which may be a component of graphics module 132, provides soft keyboards for entering text in various applications (e.g., contacts 137, e-mail 140, IM 141, browser 147, and any other application that needs text input).
GPS module 135 determines the location of the device and provides this information for use in various applications (e.g., to telephone 138 for use in location-based dialing, to camera 143 as picture/video metadata, and to applications that provide location-based services such as weather widgets, local yellow page widgets, and map/navigation widgets).
Applications 136 may include the following modules (or sets of instructions), or a subset or superset thereof:
-
- Contacts module 137 (sometimes called an address book or contact list);
- Telephone module 138;
- Video conferencing module 139;
- E-mail client module 140;
- Instant messaging (IM) module 141;
- Workout support module 142;
- Camera module 143 for still and/or video images;
- Image management module 144;
- Video player module;
- Music player module;
- Browser module 147;
- Calendar module 148;
- Widget modules 149, which may include one or more of: weather widget 149-1, stocks widget 149-2, calculator widget 149-3, alarm clock widget 149-4, dictionary widget 149-5, and other widgets obtained by the user, as well as user-created widgets 149-6;
- Widget creator module 150 for making user-created widgets 149-6;
- Search module 151;
- Video and music player module 152, which merges video player module and music player module;
- Notes module 153;
- Map module 154; and/or
- Online video module 155.
Examples of other applications 136 that may be stored in memory 102 include other word processing applications, other image editing applications, drawing applications, presentation applications, JAVA-enabled applications, encryption, digital rights management, voice recognition, and voice replication.
In conjunction with touch screen 112, display controller 156, contact/motion module 130, graphics module 132, and text input module 134, contacts module 137 may be used to manage an address book or contact list (e.g., stored in application internal state 192 of contacts module 137 in memory 102 or memory 370), including: adding name(s) to the address book; deleting name(s) from the address book; associating telephone number(s), e-mail address(es), physical address(es) or other information with a name; associating an image with a name; categorizing and sorting names; providing telephone numbers or e-mail addresses to initiate and/or facilitate communications by telephone 138, video conference module 139, e-mail 140, or IM 141; and so forth.
In conjunction with RF circuitry 108, audio circuitry 110, speaker 111, microphone 113, touch screen 112, display controller 156, contact/motion module 130, graphics module 132, and text input module 134, telephone module 138 may be used to enter a sequence of characters corresponding to a telephone number, access one or more telephone numbers in address book 137, modify a telephone number that has been entered, dial a respective telephone number, conduct a conversation and disconnect or hang up when the conversation is completed. As noted above, the wireless communication may use any of a plurality of communications standards, protocols and technologies.
In conjunction with RF circuitry 108, audio circuitry 110, speaker 111, microphone 113, touch screen 112, display controller 156, optical sensor 164, optical sensor controller 158, contact module 130, graphics module 132, text input module 134, contacts module 137, and telephone module 138, video conference module 139 includes executable instructions to initiate, conduct, and terminate a video conference between a user and one or more other participants in accordance with user instructions.
In conjunction with RF circuitry 108, touch screen 112, display controller 156, contact/motion module 130, graphics module 132, and text input module 134, e-mail client module 140 includes executable instructions to create, send, receive, and manage e-mail in response to user instructions. In conjunction with image management module 144, e-mail client module 140 makes it very easy to create and send e-mails with still or video images taken with camera module 143.
In conjunction with RF circuitry 108, touch screen 112, display controller 156, contact module 130, graphics module 132, and text input module 134, the instant messaging module 141 includes executable instructions to enter a sequence of characters corresponding to an instant message, to modify previously entered characters, to transmit a respective instant message (for example, using a Short Message Service (SMS) or Multimedia Message Service (MMS) protocol for telephony-based instant messages or using XMPP, SIMPLE, or IMPS for Internet-based instant messages), to receive instant messages and to view received instant messages. In some embodiments, transmitted and/or received instant messages may include graphics, photos, audio files, video files and/or other attachments as are supported in a MMS and/or an Enhanced Messaging Service (EMS). As used herein, “instant messaging” refers to both telephony-based messages (e.g., messages sent using SMS or MMS) and Internet-based messages (e.g., messages sent using XMPP, SIMPLE, or IMPS).
In conjunction with RF circuitry 108, touch screen 112, display controller 156, contact module 130, graphics module 132, text input module 134, GPS module 135, map module 154, and music player module, workout support module 142 includes executable instructions to create workouts (e.g., with time, distance, and/or calorie burning goals); communicate with workout sensors (sports devices); receive workout sensor data; calibrate sensors used to monitor a workout; select and play music for a workout; and display, store and transmit workout data.
In conjunction with touch screen 112, display controller 156, optical sensor(s) 164, optical sensor controller 158, contact/motion module 130, graphics module 132, and image management module 144, camera module 143 includes executable instructions to capture still images or video (including a video stream) and store them into memory 102, modify characteristics of a still image or video, or delete a still image or video from memory 102.
In conjunction with touch screen 112, display controller 156, contact/motion module 130, graphics module 132, text input module 134, and camera module 143, image management module 144 includes executable instructions to arrange, modify (e.g., edit), or otherwise manipulate, label, delete, present (e.g., in a digital slide show or album), and store still and/or video images.
In conjunction with touch screen 112, display controller 156, contact/motion module 130, graphics module 132, audio circuitry 110, and speaker 111, video player module 145 includes executable instructions to display, present or otherwise play back videos (e.g., on touch screen 112 or on an external, connected display via external port 124).
In conjunction with touch screen 112, display system controller 156, contact module 130, graphics module 132, audio circuitry 110, speaker 111, RF circuitry 108, and browser module 147, music player module 146 includes executable instructions that allow the user to download and play back recorded music and other sound files stored in one or more file formats, such as MP3 or AAC files. In some embodiments, device 100 may include the functionality of an MP3 player, such as an iPod (trademark of Apple Inc.).
In conjunction with RF circuitry 108, touch screen 112, display controller 156, contact/motion module 130, graphics module 132, and text input module 134, browser module 147 includes executable instructions to browse the Internet in accordance with user instructions, including searching, linking to, receiving, and displaying web-pages or portions thereof, as well as attachments and other files linked to web-pages.
In conjunction with RF circuitry 108, touch screen 112, display controller 156, contact/motion module 130, graphics module 132, text input module 134, e-mail client module 140, and browser module 147, calendar module 148 includes executable instructions to create, display, modify, and store calendars and data associated with calendars (e.g., calendar entries, to do lists, etc.) in accordance with user instructions.
In conjunction with RF circuitry 108, touch screen 112, display controller 156, contact/motion module 130, graphics module 132, text input module 134, and browser module 147, widget modules 149 are mini-applications that may be downloaded and used by a user (e.g., weather widget 149-1, stocks widget 149-2, calculator widget 149-3, alarm clock widget 149-4, and dictionary widget 149-5) or created by the user (e.g., user-created widget 149-6). In some embodiments, a widget includes an HTML (Hypertext Markup Language) file, a CSS (Cascading Style Sheets) file, and a JavaScript file. In some embodiments, a widget includes an XML (Extensible Markup Language) file and a JavaScript file (e.g., Yahoo! Widgets).
In conjunction with RF circuitry 108, touch screen 112, display controller 156, contact/motion module 130, graphics module 132, text input module 134, and browser module 147, the widget creator module 150 may be used by a user to create widgets (e.g., turning a user-specified portion of a web-page into a widget).
In conjunction with touch screen 112, display controller 156, contact/motion module 130, graphics module 132, and text input module 134, search module 151 includes executable instructions to search for text, music, sound, image, video, and/or other files in memory 102 that match one or more search criteria (e.g., one or more user-specified search terms) in accordance with user instructions.
In conjunction with touch screen 112, display controller 156, contact/motion module 130, graphics module 132, audio circuitry 110, speaker 111, RF circuitry 108, and browser module 147, video and music player module 152 includes executable instructions that allow the user to download and play back recorded music and other sound files stored in one or more file formats, such as MP3 or AAC files, and executable instructions to display, present, or otherwise play back videos (e.g., on touch screen 112 or on an external, connected display via external port 124). In some embodiments, device 100 optionally includes the functionality of an MP3 player, such as an iPod (trademark of Apple Inc.).
In conjunction with touch screen 112, display controller 156, contact/motion module 130, graphics module 132, and text input module 134, notes module 153 includes executable instructions to create and manage notes, to-do lists, and the like in accordance with user instructions.
In conjunction with RF circuitry 108, touch screen 112, display controller 156, contact/motion module 130, graphics module 132, text input module 134, GPS module 135, and browser module 147, map module 154 may be used to receive, display, modify, and store maps and data associated with maps (e.g., driving directions; data on stores and other points of interest at or near a particular location; and other location-based data) in accordance with user instructions.
In conjunction with touch screen 112, display controller 156, contact/motion module 130, graphics module 132, audio circuitry 110, speaker 111, RF circuitry 108, text input module 134, e-mail client module 140, and browser module 147, online video module 155 includes instructions that allow the user to access, browse, receive (e.g., by streaming and/or download), play back (e.g., on the touch screen or on an external, connected display via external port 124), send an e-mail with a link to a particular online video, and otherwise manage online videos in one or more file formats, such as H.264. In some embodiments, instant messaging module 141, rather than e-mail client module 140, is used to send a link to a particular online video. Additional description of the online video application can be found in U.S. Provisional Patent Application No. 60/936,562, “Portable Multifunction Device, Method, and Graphical User Interface for Playing Online Videos,” filed Jun. 20, 2007, and U.S. patent application Ser. No. 11/968,067, “Portable Multifunction Device, Method, and Graphical User Interface for Playing Online Videos,” filed Dec. 31, 2007, the contents of which are hereby incorporated by reference in their entirety.
Each of the above identified modules and applications corresponds to a set of executable instructions for performing one or more functions described above and the methods described in this application (e.g., the computer-implemented methods and other information processing methods described herein). These modules (e.g., sets of instructions) need not be implemented as separate software programs, procedures or modules, and thus various subsets of these modules may be combined or otherwise rearranged in various embodiments. For example, video player module may be combined with music player module into a single module (e.g., video and music player module 152, FIG. 1B). In some embodiments, memory 102 may store a subset of the modules and data structures identified above. Furthermore, memory 102 may store additional modules and data structures not described above.
In some embodiments, device 100 is a device where operation of a predefined set of functions on the device is performed exclusively through a touch screen and/or a touchpad. By using a touch screen and/or a touchpad as the primary input control device for operation of device 100, the number of physical input control devices (such as push buttons, dials, and the like) on device 100 may be reduced.
The predefined set of functions that may be performed exclusively through a touch screen and/or a touchpad include navigation between user interfaces. In some embodiments, the touchpad, when touched by the user, navigates device 100 to a main, home, or root menu from any user interface that may be displayed on device 100. In such embodiments, a “menu button” is implemented using a touchpad. In some other embodiments, the menu button is a physical push button or other physical input control device instead of a touchpad.
FIG. 1B is a block diagram illustrating exemplary components for event handling in accordance with some embodiments. In some embodiments, memory 102 (in FIG. 1A) or 370 (FIG. 3) includes event sorter 170 (e.g., in operating system 126) and a respective application 136-1 (e.g., any of the aforementioned applications 137-151, 155, 380-390).
Event sorter 170 receives event information and determines the application 136-1 and application view 191 of application 136-1 to which to deliver the event information. Event sorter 170 includes event monitor 171 and event dispatcher module 174. In some embodiments, application 136-1 includes application internal state 192, which indicates the current application view(s) displayed on touch sensitive display 112 when the application is active or executing. In some embodiments, device/global internal state 157 is used by event sorter 170 to determine which application(s) is(are) currently active, and application internal state 192 is used by event sorter 170 to determine application views 191 to which to deliver event information.
In some embodiments, application internal state 192 includes additional information, such as one or more of: resume information to be used when application 136-1 resumes execution, user interface state information that indicates information being displayed or that is ready for display by application 136-1, a state queue for enabling the user to go back to a prior state or view of application 136-1, and a redo/undo queue of previous actions taken by the user.
Event monitor 171 receives event information from peripherals interface 118. Event information includes information about a sub-event (e.g., a user touch on touch-sensitive display 112, as part of a multi-touch gesture). Peripherals interface 118 transmits information it receives from I/O subsystem 106 or a sensor, such as proximity sensor 166, accelerometer(s) 168, and/or microphone 113 (through audio circuitry 110). Information that peripherals interface 118 receives from I/O subsystem 106 includes information from touch-sensitive display 112 or a touch-sensitive surface.
In some embodiments, event monitor 171 sends requests to the peripherals interface 118 at predetermined intervals. In response, peripherals interface 118 transmits event information. In other embodiments, peripherals interface 118 transmits event information only when there is a significant event (e.g., receiving an input above a predetermined noise threshold and/or for more than a predetermined duration). In some embodiments, event sorter 170 also includes a hit view determination module 172 and/or an active event recognizer determination module 173.
Hit view determination module 172 provides software procedures for determining where a sub-event has taken place within one or more views, when touch sensitive display 112 displays more than one view. Views are made up of controls and other elements that a user can see on the display.
Another aspect of the user interface associated with an application is a set of views, sometimes herein called application views or user interface windows, in which information is displayed and touch-based gestures occur. The application views (of a respective application) in which a touch is detected may correspond to programmatic levels within a programmatic or view hierarchy of the application. For example, the lowest level view in which a touch is detected may be called the hit view, and the set of events that are recognized as proper inputs may be determined based, at least in part, on the hit view of the initial touch that begins a touch-based gesture.
Hit view determination module 172 receives information related to sub-events of a touch-based gesture. When an application has multiple views organized in a hierarchy, hit view determination module 172 identifies a hit view as the lowest view in the hierarchy which should handle the sub-event. In most circumstances, the hit view is the lowest level view in which an initiating sub-event occurs (e.g., the first sub-event in the sequence of sub-events that form an event or potential event). Once the hit view is identified by the hit view determination module 172, the hit view typically receives all sub-events related to the same touch or input source for which it was identified as the hit view.
Active event recognizer determination module 173 determines which view or views within a view hierarchy should receive a particular sequence of sub-events. In some embodiments, active event recognizer determination module 173 determines that only the hit view should receive a particular sequence of sub-events. In other embodiments, active event recognizer determination module 173 determines that all views that include the physical location of a sub-event are actively involved views, and therefore determines that all actively involved views should receive a particular sequence of sub-events. In other embodiments, even if touch sub-events were entirely confined to the area associated with one particular view, views higher in the hierarchy would still remain as actively involved views.
Event dispatcher module 174 dispatches the event information to an event recognizer (e.g., event recognizer 180). In embodiments including active event recognizer determination module 173, event dispatcher module 174 delivers the event information to an event recognizer determined by active event recognizer determination module 173. In some embodiments, event dispatcher module 174 stores in an event queue the event information, which is retrieved by a respective event receiver 182.
In some embodiments, operating system 126 includes event sorter 170. Alternatively, application 136-1 includes event sorter 170. In yet other embodiments, event sorter 170 is a stand-alone module, or a part of another module stored in memory 102, such as contact/motion module 130.
In some embodiments, application 136-1 includes a plurality of event handlers 190 and one or more application views 191, each of which includes instructions for handling touch events that occur within a respective view of the application's user interface. Each application view 191 of the application 136-1 includes one or more event recognizers 180. Typically, a respective application view 191 includes a plurality of event recognizers 180. In other embodiments, one or more of event recognizers 180 are part of a separate module, such as a user interface kit (not shown) or a higher level object from which application 136-1 inherits methods and other properties. In some embodiments, a respective event handler 190 includes one or more of: data updater 176, object updater 177, GUI updater 178, and/or event data 179 received from event sorter 170. Event handler 190 may utilize or call data updater 176, object updater 177, or GUI updater 178 to update the application internal state 192. Alternatively, one or more of the application views 191 include one or more respective event handlers 190. Also, in some embodiments, one or more of data updater 176, object updater 177, and GUI updater 178 are included in a respective application view 191.
A respective event recognizer 180 receives event information (e.g., event data 179) from event sorter 170 and identifies an event from the event information. Event recognizer 180 includes event receiver 182 and event comparator 184. In some embodiments, event recognizer 180 also includes at least a subset of: metadata 183, and event delivery instructions 188 (which may include sub-event delivery instructions).
Event receiver 182 receives event information from event sorter 170. The event information includes information about a sub-event, for example, a touch or a touch movement. Depending on the sub-event, the event information also includes additional information, such as location of the sub-event. When the sub-event concerns motion of a touch the event information may also include speed and direction of the sub-event. In some embodiments, events include rotation of the device from one orientation to another (e.g., from a portrait orientation to a landscape orientation, or vice versa), and the event information includes corresponding information about the current orientation (also called device attitude) of the device.
Event comparator 184 compares the event information to predefined event or sub-event definitions and, based on the comparison, determines an event or sub-event, or determines or updates the state of an event or sub-event. In some embodiments, event comparator 184 includes event definitions 186. Event definitions 186 contain definitions of events (e.g., predefined sequences of sub-events), for example, event 1 (187-1), event 2 (187-2), and others. In some embodiments, sub-events in an event (187) include, for example, touch begin, touch end, touch movement, touch cancellation, and multiple touching. In one example, the definition for event 1 (187-1) is a double tap on a displayed object. The double tap, for example, comprises a first touch (touch begin) on the displayed object for a predetermined phase, a first liftoff (touch end) for a predetermined phase, a second touch (touch begin) on the displayed object for a predetermined phase, and a second liftoff (touch end) for a predetermined phase. In another example, the definition for event 2 (187-2) is a dragging on a displayed object. The dragging, for example, comprises a touch (or contact) on the displayed object for a predetermined phase, a movement of the touch across touch-sensitive display 112, and liftoff of the touch (touch end). In some embodiments, the event also includes information for one or more associated event handlers 190.
In some embodiments, event definitions 187 include a definition of an event for a respective user-interface object. In some embodiments, event comparator 184 performs a hit test to determine which user-interface object is associated with a sub-event. For example, in an application view in which three user-interface objects are displayed on touch-sensitive display 112, when a touch is detected on touch-sensitive display 112, event comparator 184 performs a hit test to determine which of the three user-interface objects is associated with the touch (sub-event). If each displayed object is associated with a respective event handler 190, the event comparator uses the result of the hit test to determine which event handler 190 should be activated. For example, event comparator 184 selects an event handler associated with the sub-event and the object triggering the hit test.
In some embodiments, the definition for a respective event (187) also includes delayed actions that delay delivery of the event information until after it has been determined whether the sequence of sub-events does or does not correspond to the event recognizer's event type.
When a respective event recognizer 180 determines that the series of sub-events do not match any of the events in event definitions 186, the respective event recognizer 180 enters an event impossible, event failed, or event ended state, after which it disregards subsequent sub-events of the touch-based gesture. In this situation, other event recognizers, if any, that remain active for the hit view continue to track and process sub-events of an ongoing touch-based gesture.
In some embodiments, a respective event recognizer 180 includes metadata 183 with configurable properties, flags, and/or lists that indicate how the event delivery system should perform sub-event delivery to actively involved event recognizers. In some embodiments, metadata 183 includes configurable properties, flags, and/or lists that indicate how event recognizers may interact, or are enabled to interact, with one another. In some embodiments, metadata 183 includes configurable properties, flags, and/or lists that indicate whether sub-events are delivered to varying levels in the view or programmatic hierarchy.
In some embodiments, a respective event recognizer 180 activates event handler 190 associated with an event when one or more particular sub-events of an event are recognized. In some embodiments, a respective event recognizer 180 delivers event information associated with the event to event handler 190. Activating an event handler 190 is distinct from sending (and deferred sending) sub-events to a respective hit view. In some embodiments, event recognizer 180 throws a flag associated with the recognized event, and event handler 190 associated with the flag catches the flag and performs a predefined process.
In some embodiments, event delivery instructions 188 include sub-event delivery instructions that deliver event information about a sub-event without activating an event handler. Instead, the sub-event delivery instructions deliver event information to event handlers associated with the series of sub-events or to actively involved views. Event handlers associated with the series of sub-events or with actively involved views receive the event information and perform a predetermined process.
In some embodiments, data updater 176 creates and updates data used in application 136-1. For example, data updater 176 updates the telephone number used in contacts module 137, or stores a video file used in video player module. In some embodiments, object updater 177 creates and updates objects used in application 136-1. For example, object updater 177 creates a new user-interface object or updates the position of a user-interface object. GUI updater 178 updates the GUI. For example, GUI updater 178 prepares display information and sends it to graphics module 132 for display on a touch-sensitive display.
In some embodiments, event handler(s) 190 includes or has access to data updater 176, object updater 177, and GUI updater 178. In some embodiments, data updater 176, object updater 177, and GUI updater 178 are included in a single module of a respective application 136-1 or application view 191. In other embodiments, they are included in two or more software modules.
It shall be understood that the foregoing discussion regarding event handling of user touches on touch-sensitive displays also applies to other forms of user inputs to operate multifunction devices 100 with input devices, not all of which are initiated on touch screens. For example, mouse movement and mouse button presses, optionally coordinated with single or multiple keyboard presses or holds; contact movements such as taps, drags, scrolls, etc. on touchpads; pen stylus inputs; movement of the device; oral instructions; detected eye movements; biometric inputs; and/or any combination thereof are optionally utilized as inputs corresponding to sub-events which define an event to be recognized.
FIG. 2 illustrates a portable multifunction device 100 having a touch screen 112 in accordance with some embodiments. The touch screen may display one or more graphics within user interface (UI) 200. In this embodiment, as well as others described below, a user may select one or more of the graphics by making contact or touching the graphics, for example, with one or more fingers 202 (not drawn to scale in the figure) or one or more styluses 203 (not drawn to scale in the figure). In some embodiments, selection of one or more graphics occurs when the user breaks contact with the one or more graphics. In some embodiments, the contact may include a gesture, such as one or more taps, one or more swipes (from left to right, right to left, upward and/or downward) and/or a rolling of a finger (from right to left, left to right, upward and/or downward) that has made contact with device 100. In some embodiments, inadvertent contact with a graphic may not select the graphic. For example, a swipe gesture that sweeps over an application icon may not select the corresponding application when the gesture corresponding to selection is a tap.
Device 100 may also include one or more physical buttons, such as “home” or menu button 204. As described previously, menu button 204 may be used to navigate to any application 136 in a set of applications that may be executed on device 100. Alternatively, in some embodiments, the menu button is implemented as a soft key in a GUI displayed on touch screen 112.
In one embodiment, device 100 includes touch screen 112, menu button 204, push button 206 for powering the device on/off and locking the device, volume adjustment button(s) 208, Subscriber Identity Module (SIM) card slot 210, head set jack 212, and docking/charging external port 124. Push button 206 may be used to turn the power on/off on the device by depressing the button and holding the button in the depressed state for a predefined time interval; to lock the device by depressing the button and releasing the button before the predefined time interval has elapsed; and/or to unlock the device or initiate an unlock process. In an alternative embodiment, device 100 also may accept verbal input for activation or deactivation of some functions through microphone 113.
FIG. 3 is a block diagram of an exemplary multifunction device with a display and a touch-sensitive surface in accordance with some embodiments. Device 300 need not be portable. In some embodiments, device 300 is a laptop computer, a desktop computer, a tablet computer, a multimedia player device, a navigation device, an educational device (such as a child's learning toy), a gaming system, or a control device (e.g., a home or industrial controller). Device 300 typically includes one or more processing units (CPU's) 310, one or more network or other communications interfaces 360, memory 370, and one or more communication buses 320 for interconnecting these components. Communication buses 320 may include circuitry (sometimes called a chipset) that interconnects and controls communications between system components. Device 300 includes input/output (I/O) interface 330 comprising display 340, which is typically a touch screen display. I/O interface 330 also may include a keyboard and/or mouse (or other pointing device) 350 and touchpad 355. Memory 370 includes high-speed random access memory, such as DRAM, SRAM, DDR RAM or other random access solid state memory devices; and may include non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. Memory 370 may optionally include one or more storage devices remotely located from CPU(s) 310. In some embodiments, memory 370 stores programs, modules, and data structures analogous to the programs, modules, and data structures stored in memory 102 of portable multifunction device 100 (FIG. 1), or a subset thereof. Furthermore, memory 370 may store additional programs, modules, and data structures not present in memory 102 of portable multifunction device 100. For example, memory 370 of device 300 may store drawing module 380, presentation module 382, word processing module 384, website creation module 386, disk authoring module 388, and/or spreadsheet module 390, while memory 102 of portable multifunction device 100 (FIG. 1) may not store these modules.
Each of the above identified elements in FIG. 3 may be stored in one or more of the previously mentioned memory devices. Each of the above identified modules corresponds to a set of instructions for performing a function described above. The above identified modules or programs (i.e., sets of instructions) need not be implemented as separate software programs, procedures or modules, and thus various subsets of these modules may be combined or otherwise re-arranged in various embodiments. In some embodiments, memory 370 may store a subset of the modules and data structures identified above. Furthermore, memory 370 may store additional modules and data structures not described above.
Attention is now directed towards embodiments of user interfaces (“UI”) that may be implemented on portable multifunction device 100. FIG. 4A illustrates exemplary user interfaces for a menu of applications on portable multifunction device 100 in accordance with some embodiments. Similar user interfaces may be implemented on device 300. In some embodiments, user interface 400 includes the following elements, or a subset or superset thereof:
-
- Signal strength indicator(s) 402 for wireless communication(s), such as cellular and Wi-Fi signals;
- Time 404;
- Bluetooth indicator 405;
- Battery status indicator 406;
- Tray 408 with icons for frequently used applications, such as:
- Icon 416 for telephone module 138, labeled “Phone,” which optionally includes an indicator 414 of the number of missed calls or voicemail messages;
- Icon 418 for e-mail client module 140, labeled “Mail,” which optionally includes an indicator 410 of the number of unread e-mails;
- Icon 420 for browser module 147, labeled “Browser;” and
- Icon 422 for video and music player module 152, also referred to as iPod (trademark of Apple Inc.) module 152, labeled “iPod;” and
- Icons for other applications, such as:
- Icon 424 for IM module 141, labeled “Messages;”
- Icon 426 for calendar module 148, labeled “Calendar;”
- Icon 428 for image management module 144, labeled “Photos;”
- Icon 430 for camera module 143, labeled “Camera;”
- Icon 432 for online video module 155, labeled “Online Video;”
- Icon 434 for stocks widget 149-2, labeled “Stocks;”
- Icon 436 for map module 154, labeled “Maps;”
- Icon 438 for weather widget 149-1, labeled “Weather;”
- Icon 440 for alarm clock widget 149-4, labeled “Clock;”
- Icon 442 for workout support module 142, labeled “Workout Support;”
- Icon 444 for notes module 153, labeled “Notes;” and
- Icon 446 for a settings application or module, labeled “Settings,” which provides access to settings for device 100 and its various applications 136.
FIG. 4B illustrates an exemplary user interface on a device (e.g., device 300, FIG. 3) with a touch-sensitive surface 451 (e.g., a tablet or touchpad 355, FIG. 3) that is separate from the display 450 (e.g., touch screen display 112). Although many of the examples which follow will be given with reference to inputs on touch screen display 112 (where the touch sensitive surface and the display are combined), in some embodiments, the device detects inputs on a touch-sensitive surface that is separate from the display, as shown in FIG. 4B. In some embodiments the touch sensitive surface (e.g., 451) has a primary axis (e.g., 452) that corresponds to a primary axis (e.g., 453) on the display (e.g., 450). In accordance with these embodiments, the device detects contacts (e.g., 460 and 462) with the touch-sensitive surface 451 at locations that correspond to respective locations on the display (e.g., 460 corresponds to 468 and 462 corresponds to 470). In this way, user inputs (e.g., contacts 460 and 462, and movements thereof) detected by the device on the touch-sensitive surface (e.g., 451) are used by the device to manipulate the user interface on the display (e.g., 450) of the multifunction device when the touch-sensitive surface is separate from the display. It should be understood that similar methods may be used for other user interfaces described herein.
Additionally, while the following examples are given primarily with reference to finger inputs (e.g., finger contacts, finger tap gestures, finger swipe gestures), it should be understood that, in some embodiments, one or more of the finger inputs are replaced with input from another input device (e.g., a mouse-based input or stylus input). For example, a swipe gesture is, optionally, replaced with a mouse click (e.g., instead of a contact) followed by movement of the cursor along the path of the swipe (e.g., instead of movement of the contact). As another example, a tap gesture is, optionally, replaced with a mouse click while the cursor is located over the location of the tap gesture (e.g., instead of detection of the contact followed by ceasing to detect the contact). Similarly, when multiple user inputs are simultaneously detected, it should be understood that multiple computer mice are, optionally, used simultaneously, or a mouse and finger contacts are, optionally, used simultaneously.
As used in the specification and claims, the term “open application” refers to a software application with retained state information (e.g., as part of device/global internal state 157 and/or application internal state 192). An open (e.g., executing) application is any one of the following types of applications:
-
- an active application, which is currently displayed on display 112 (or a corresponding application view is currently displayed on the display);
- a background application (or background process), which is not currently displayed on display 112, but one or more application processes (e.g., instructions) for the corresponding application are being processed by one or more processors 120 (i.e., running);
- a suspended application, which is not currently running, and the application is stored in a volatile memory (e.g., DRAM, SRAM, DDR RAM, or other volatile random access solid state memory device of memory 102); and
- a hibernated application, which is not running, and the application is stored in a non-volatile memory (e.g., one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices of memory 102).
As used herein, the term “closed application” refers to software applications without retained state information (e.g., state information for closed applications is not stored in a memory of the device). Accordingly, closing an application includes stopping and/or removing application processes for the application and removing state information for the application from the memory of the device. Generally, opening a second application while in a first application does not close the first application. When the second application is displayed and the first application ceases to be displayed, the first application becomes a background application.
FIG. 5 illustrates an exemplary schematic block diagram of a phrase embedding system 500 in accordance with some embodiments. The phrase embedding system 500 may be implemented using one or more multifunction devices including but not limited to devices 100, 400, and 9 900 (FIGS. 1A, 2, 4A-B, and 9).
Generally, the phrase embedding system 500 operates to provide phrase representations, for instance in a continuous space (e.g., vector space), that may be used to perform a variety of natural language processing (NLP) tasks. In some examples, providing phrase representations in this manner includes determining which phrases of a sentence (or sentences) are relatively discriminative and/or parsimonious in meaning.
In some embodiments, the phrase embedding system 500 operates at a sentence-level. For example, the phrase embedding system 500 may consider each phrase of each of a plurality of sentences in isolation such that phrases spanning between sentences are not considered. The phrase embedding system 500 may embed phrases of each of a plurality of sentences identified in a set of data (e.g., training data) provided and/or stored on a device on which the phrase embedding system 500 is implemented.
In operation, the phrase embedding system, 500 may identify a sentence in a set of data and provide each word of the sentence to a respective embedding unit 502. Briefly, each of the embedding units 502 may map the received word to a word representation (e.g., vector). Mapping a word in this manner may include embedding (e.g., orthographically embedding) a character sequence of the word to provide a word representation of the word in a continuous space. Such embedding further may ignore homonymous and/or polysemous aspects of a word. By way of example, two words having a same character sequence, but a different meaning or context, may be mapped to a same word representation in the continuous space. In some examples, one or more of the embedding units 502 may be implemented using a neural network, such as a recurrent neural network (e.g., bidirectional recurrent neural network) or a feedforward neural network.
The concatenation unit 504 receives each of the word representations from the embedding units 502 and provides (e.g., generates) a plurality of phrases based on the word representations. Because phrases provided in this manner are based on word representations of words, the phrases may comprise phrase representations in the continuous space (e.g., the same space as the word representations). In some examples, each phrase is provided by concatenating word representations of each word included in the phrase. Concatenating in this manner may result in a phrase having a relatively high dimensionality relative to word representations used to provide the phrase. As an example, if each word representation used to provide a phrase including five word representations has a dimension 2H, the phrase will have a dimension of 10H.
In some examples, the concatenation unit 504 provides a phrase for each word of a sentence (each word of a sentence is used as a center word of a phrase), and each phrase may have a same length, for instance, based on a length factor L. The length factor L may specify the amount of left context and right context of a word included in a phrase. Accordingly, each phrase may have a length of 2L+1. Left context of a word may include word representations of words preceding the word in the sentence and right context of the word may include word representations of words following the word in the sentence. As an example in which L=3, in the phrase “necessary to succeed in the high-tech industry,” “in” serves as the center word of the phrase, “necessary to succeed” serves as the left context of the word, and “the high-tech industry” serves as the right context of the word. Because a phrase may be provided for each word of a sentence and because each phrase may have a same length, it will be appreciated that phrases corresponding to a same sentence may include one or more of the same word representations. Moreover, for phrases in which one or more forms of context is not available (e.g., L is greater than the number of words preceding and/or following a center word of the phrase in the sentence), word representations may make use of one or more special symbols (e.g., <s>) in lieu of the unavailable context.
The autoencoder 506 receives each of the phrases from the concatenation unit 504 and based on the phrases, provides a respective plurality of encoded phrases. In some examples, each of the phrases may have a representation of a first type (e.g., a first dimension) and each of the encoded phrases may have a representation of a second type (e.g., a second dimension different than the first dimension).
As described, each of the phrases provided by the concatenation unit 504 may have a relatively high dimensionality as a result of concatenation of word representations. Accordingly, in some instances, the autoencoder 506 adjusts (e.g., reduces) dimensionality of each of the phrases to provide the plurality of encoded phrases. Adjusting dimensionality of a phrase in this manner may include reducing a dimensionality of the phrase and reconstructing the phrase. In some examples, the autoencoder 506 may be implemented using a neural network, such as a recurrent neural network or a feedforward neural network. Accordingly, the autoencoder 506 may reduce the dimensionality of a phrase using a first weight factor (e.g., a weight matrix) and reconstruct the phrase using a second weight factor. In some examples, the autoencoder 506 may reduce dimensionality of the phrase using multiple weight factors and/or may reconstruct the phrase using multiple weight factors. By reducing dimensionality and reconstructing in this manner, the autoencoder may provide encoded phrases with minimal reconstruction errors.
The averaging unit 508 receives each of the encoded phrases from the autoencoder 506 and provides an average of the encoded phrases that serves as a representation of the sentence. In some examples, providing an average may include providing a centroid of each of the plurality of encoded phrases.
As described, the phrase embedding system 508 may operate at a sentence level, and a plurality of sentences may be identified in a set of data. Accordingly, the operation described herein may be iteratively repeated until the averaging unit 508 has provided an average for each of the plurality of sentences identified in the set of data.
The clustering unit 510 receives each of the averages (e.g., centroids) and clusters the averages in the continuous space. The clustering unit 510 may cluster the averages using one or more clustering algorithms known in the art, including but not limited to, a hierarchical k-nearest-neighbor clustering algorithm, a K-means clustering algorithm, a hierarchical clustering algorithm, a sparse exemplar-based modeling algorithm, or a combination thereof. As an example, the clustering unit 510 may use a K-means clustering algorithm to provide a first iteration of clustering (e.g., a coarse cluster partitioning) and may use a hierarchical clustering algorithm to provide a second iteration of clustering (e.g., a fine cluster partitioning).
The entropy computation unit 512 identifies (e.g., determines) an indexing power of each encoded phrase of each sentence of the set of data, for instance, using the clusters provided by the clustering unit 510. In some examples, the entropy computation unit 512 may determine an indexing power of a phrase based on the number of times the center word of the phrase occurs in each of the clusters. Generally, the fewer the number of clusters in which a center word of a phrase is found, the more discriminative the phrase.
In some examples, the entropy computation unit 512 may determine indexing power using normalized entropy of a center word of each phrase. The normalized entropy, εi, of a word may be determined in accordance with the following equation:
where K represents the number of clusters in the continuous space, Ci,k represents the number of times a center word wi appears in a cluster Ck, and ti represents the total number of times center word wi appears in all clusters. By definition, the normalized entropy εi will have a value greater than or equal to 0 and less than or equal to 1 (i.e., 0≦εi≦1).
Having determined the normalized entropy εi, the entropy computation unit 512 may determine the indexing power of each encoded phrase. Because greater normalized entropy values are associated with less discriminative phrases (e.g., phrases included in many clusters) and lesser normalized entropy values are associated with more discriminative phrases (e.g., phrases included in few clusters), the indexing power of each phrase may be determined by subtracting the normalized entropy of each phrase from a value of 1 (i.e., 1−εi). Briefly, the greater an indexing power, the more discriminative the phrase associated with the indexing power.
The filter 514 receives each of the encoded phrases from the autoencoder 506 and each of the indexing powers associated with each of the encoded phrases from the entropy computation unit 512. Based on the indexing powers, the filter 514 may identify (e.g., select) one or more of the encoded phrases to provide as a set of parsimonious (e.g., discriminatory) phrases. In some examples, the filter may select encoded phrases having an indexing power satisfying (e.g., equal to or greater than) a threshold. In other examples, the filter may select a set of the encoded phrases having the highest indexing power (e.g., a set comprising the 20% of encoded phrases having the greatest indexing power).
Having identified one or more parsimonious phrases from the set of data, the identified parsimonious phrases may be used in one more natural language processing tasks to identify, categorize, or otherwise interpret natural language input. Such tasks may include information retrieval, document classification, question answering, and/or connectionist language modeling.
In contrast to previous embedding systems directed to embedding individual words, the embedding system 500 described herein may embed phrases, each of which includes a respective plurality of words. As a result, more intuitive and discriminative language models may be provided. Use of such language models may provide for a more discriminative evaluation of words typically ambiguous to existing systems, such as homonymous words (e.g., bank) and words that may be improperly spelled without an accent (e.g., résumé). Such models may in principle be more robust across domains and as a result provide a higher degree of re-usability (e.g., the model may be used multiple times after being trained once). In some examples, words in phrase-embedded language models may be positioned in vector space such that words with same or similar meanings are relatively proximate. In this manner, words may be interpreted based, at least in part, on meaning rather than merely spelling or pronunciation as in existing systems.
As described, the phrase embedding system 500 may operate at a sentence-level. By operating at a sentence-level, the phrase embedding system 500 need not consider inter-sentence phrases. It will be appreciated, however, that in other examples the phrase embedding system 500 may operate at one or more other levels (e.g., paragraph-level) such that phrases spanning between sentences may be utilized as described herein.
FIG. 6 illustrates an exemplary network 600 for embedding words in accordance with some embodiments. Generally, the network 600 may be a neural network (e.g., bidirectional recurrent neural network) that may serve to provide a spatial representation of a character sequence (e.g., word) in response to receipt of the character sequence. Accordingly, the network 600 may be used to implement one or more embedding units 502 of FIG. 5.
The network 600 may include multiple layers. The network 600 may, for instance, include an input layer 610, one or more hidden layers 620, and an output layer 630. In this example, network 600 includes a single hidden layer 620. It will be appreciated, however, that in other examples, the network 600 can include one more additional hidden layers 620.
Each layer of the network 600 may comprise any number of units. A layer may, for instance, comprise a single unit or may comprise multiple units. These units, which in some examples may be referred to as dimensions, neurons, or nodes (e.g., context nodes), may operate as the computational elements of the network 600. As illustrated, in some examples, the input layer 610 may include preceding context units 612, 616 and a current input unit 614, and the hidden layer 620 may include current context units 622, 624. Units of the network 600 further may be interconnected using connections. Connections may be unidirectional or bidirectional, and further may be associated with a respective weight value. Each weight value specifies a strength of the corresponding connection and accordingly the relative influence of the value provided via the connection. As illustrated, the preceding context unit 612 may be connected to the current context unit 622, the current input unit 614 may be connected to each of the current context units 622, 624, and the preceding context unit 616 may be connected to the current context unit 624. Each of the current context units 622, 624 may further be connected to the output layer 630 (recall that a layer may comprise a single unit).
In operation, the input layer 610 receives a sequence of characters and provides values corresponding the sequence to the hidden layer 620 via connections interconnected between units of the input layer 610 and the hidden layer 620. For example, each of preceding context units 612, 616 are connected to respective current context units of hidden layer 620 and provide respective context values of a current input (e.g., a current character) at a time step (e.g., time step t). In particular, preceding context unit 612 provides a first preceding context value of a current input, or lc(t−1). The preceding context value lc(t−1) may be a left preceding context value and accordingly may correspond to a left context value of the preceding time step (e.g., time step t−1). Similarly, the current input unit 614 provides a second preceding context value of a current input, or rc(t−1). The preceding context value rc(t−1) may be a right preceding context value and accordingly may correspond to a right context value of the preceding time step (e.g., time step t−1). Each of the preceding context values lc(t−1), rc(t−1) may be provided as vectors having a dimension H. The current input unit 614 is connected to current context units 622, 624 of hidden layer 620 and provides a current input, or x(t), to each of the current context units 622, 624. Generally, x(t) may be provided by encoding a current character using 1-of-M encoding and accordingly may have a dimension equal to M.
The current context unit 622 of the hidden layer 620 receives the first preceding context value lc(t−1) from the preceding context unit 612 and the current input x(t) from the current input unit 614 and based on the values determines a first current context value lc(t). The first current context value lc(t) may be a left current context value and accordingly may correspond to a left context value of a current time step (e.g., time step t). As described, in some examples, connections may be weighted. The connection between the preceding context unit 612 and the current context unit 622 may be weighted by a weight factor (e.g., weight matrix) V and the connection between the current input unit 614 and the current context unit 622 may be weighted by a weight factor X. Accordingly, the current context unit 622 may determine the left current context value lc(t) in accordance with the following formula:
lc(t)=F{X·x(t)+V·lc(t−1)}
where F{ } denotes an function (e.g., activation function), such as a sigmoid function, a hyperbolic tangent function, a rectified linear unit function, any function related thereto, or any combination thereof. The left current context value lc(t) may be provided as vector of dimension H.
Similarly, the current context unit 624 of the hidden layer 620 receives the second preceding context value rc(t−1) from the preceding context unit 616 and the current input x(t) from the current input unit 614 and based on the values determines a second current context value rc(t). The second current context value rc(t) may be a right current context value and accordingly may correspond to a right context value of a current time step (e.g., time step t). The connection between the unit 616 and the current context unit 624 may be weighted by a weight factor W and the connection between the unit 614 and the current context unit 624 may be weighted by a weight factor Y. Accordingly, the current context unit 624 may determine the right current context value rc(t) in accordance with the following formula:
rc(t)=F{Y·x(t)+W·rc(t−1)}
where F{ } denotes an activation function, such as a sigmoid function, a hyperbolic tangent function, a rectified linear unit function, or any combination thereof. The right current context value rc(t) may be provided as vector of dimension H.
In some examples, the current context values lc(t), rc(t) are concatenated, for instance, by one or more units of the hidden layer 620, to provide a state value s(t) (e.g., where s(t)=[lc(t) rc(t)]). The state value s(t) may, for instance, be indicative of a state of the network 600 and have a dimension of 2H. The state value s(t) may be provided to the output layer 630, which may in turn provide an input sequence z(t) based on the state value s(t). In some examples, the state value s(t) may be provided to the output layer 630 using a connection weighted by a weight factor Z. Accordingly, the output layer 630 may be determine the input sequence z(t) in accordance with the following formula:
z(t)=G{Z·s(t)}
where G{ } denotes a function, such as a softmax activation function. In this manner, the input sequence z(t) may be encoded using 1-of-N encoding and have a dimension of N. In some examples, N may be the size of a vocabulary to which a character sequence (word) belongs.
As described, each of the preceding context units 612, 616 provide a respective preceding context value of the current input to a respective current context unit 622, 624 of the hidden layer 620. Accordingly, the current context unit 622 may provide each current context value lc(t) of a current time step to the preceding context unit 612 of the input layer 610 for use as a preceding context value lc(t−1) during the next time step (e.g., time step t+1). Similarly, the current context unit 624 may provide each current context value rc(t) of a current time step to the preceding context unit 616 of the input layer 610 for use as a preceding context value rc(t−1) during the next time step. In this manner, the network 600 may operate recurrently and/or bidirectionally to provide a spatial representation of a character sequence.
FIG. 7 illustrates an exemplary encoder 700 in accordance with some embodiments. The encoder 700 may be a neural network (e.g., neural network autoencoder) that may serve to adjust a dimensionality of a phrase. Accordingly, the encoder 700 may be used to implement the autoencoder 506 of FIG. 5.
The encoder 700 may include multiple layers. The encoder 700 may, for instance, include an input layer 710, a compression layer 720, a bottleneck layer 730, an expansion layer 740, and an output layer 750. In some instances, one or more of the compression layer 720, bottleneck layer 730, and expansion layer 740 may be referred to as hidden layers. It will be appreciated that in other examples, the encoder 700 can include any number of additional layers (e.g., additional hidden layers) or omit one or more of the layers 710-750.
Each layer of the encoder 700 may comprise any number of units (not shown in FIG. 10). These units, which may be referred to as dimensions, neurons, or nodes (e.g., context nodes), operate as the computational elements of the encoder 1000. As illustrated, in some examples, layers (or units included therein) may be interconnected using connections. Each connection may be associated with a respective weight value that specifies a strength of the corresponding connection and accordingly the relative influence of the value provided via the connection. As illustrated, the input layer 710 may be connected to the compression layer 720, the compression layer 720 may be connected to the bottleneck layer 730, the bottleneck layer 730 may be connected to the expansion layer 740, and the expansion layer 740 may be connected to the output layer 750.
Generally, the encoder 700 reduces dimensionality by projecting a phrase to a lower dimension. For example, the input layer 710 receives a phrase p. The phrase p may, for instance, have a dimension of P, or 2H(2L+1), where 2L corresponds to the context included in the phrase.
The input layer 710 may provide the phrase p to the compression layer 720. Based on the phrase p, the compression layer 720 may provide a phrase c. In some examples, the connection between the input layer 710 and the compression layer 720 may be weighted by a weight factor (e.g., weight matrix) U. Accordingly, the compression layer 720 may provide the phrase c in accordance with the following equation:
c=F{U·p}
where F{ } denotes an activation function. The phrase c may have a dimension of C, where C<P.
The compression layer 720 may provide the phrase c to the bottleneck layer 730. Based on the phrase c, the bottleneck layer 730 may provide the phrase b. In some examples, the connection between the compression layer 720 and the bottleneck layer 730 may be weighted by a weight factor T. Accordingly, the bottleneck layer 730 may provide the phrase b in accordance with the following equation:
b=F{T·c}
where F{ } denotes an activation function. The phrase b may have a dimension of B, where B<C<P.
Having reduced the dimensionality P of the phrase p to a dimensionality B of the phrase b, the encoder 700 may subsequently provide a reconstructed phrase p (designated as phrase p′) using the phrase b.
The bottleneck layer 730 may provide the phrase b to the expansion layer 740. Based on the phrase b, the expansion layer 740 may provide the spatial representation a. In some examples, the connection between the bottleneck layer 730 and the expansion layer 740 may be weighted by a weight factor S. Accordingly, the expansion layer 740 may provide the spatial representation a in accordance with the following equation:
a=F{S·b}
where F{ } denotes an activation function. The embedding of the spatial representation a may have a dimension of B, where B<C<P, and the spatial representation a itself may have a dimension of A.
The expansion layer 740 may provide the spatial representation a to the output layer 750. Based on the spatial representation a, the output layer 750 may provide the phrase p′, or the reconstructed spatial representation of p. In some examples, the connection between the expansion layer 740 and the output layer 750 may be weighted by a weight factor R. Accordingly, the output layer 750 may provide the phrase p′ in accordance with the following equation:
p′=F{R·a}
where F{ } denotes an activation function. The embedding of the phrase p′ may have a dimension of B, where B<C<P, and the spatial representation p′ itself may have a dimension of P.
In this manner, the encoder 700 may reduce dimensionality of phrases and/or reconstruct phrases having the reduced dimensionality. Performing dimensionality reduction in this manner can be desirable to reduce the time and cost for computations associated with the reduced-dimension spatial representation.
As described, one or more of the layers of the encoder 700 may include one or more units. In some examples, the manner in which dimensionality of vectors is reduced by the encoder 700 may depend on a relationship between the number of units in each layer. By way of example, the compression layer may have fewer units than the input layer and the dimensionality of the phrase p may be reduced based on the ratio of the number of units of the compression and the number of units in the input layer.
FIG. 8 illustrates a flow diagram of an exemplary process 800 for embedding phrases in accordance with some embodiments. The process 800 may be performed using one or more devices 122, 100, 400, and 900 (FIGS. 1A, 2, 4A-B, and 9), and further may be performed using a phrase embedding system, such as the phrase embedding system 500 of FIG. 5, implemented on the one or more devices. Operations in process 800 are, optionally, combined and/or the order of some operations is, optionally, changed.
At block 805, the device receives a plurality of words. Each of the plurality of words may arranged in one or more sentences and further may be included in a set of data, such as a set of training data. The set of data may comprise one or more documents (e.g., text documents) and/or one or more data structures.
At block 810, the device maps each of the plurality of words to a word representation (e.g., spatial representation, vector). In some embodiments, mapping each of the plurality of words includes orthographically embedding each of the plurality of words, for instance to a word representation, in a continuous space. One or more of the plurality of words may be mapped without regard to polysemy and/or homomyny, and as a result, words having a same spelling and/or context may be mapped to a same word representation.
At block 815, the device associates each of the mapped words to provide a plurality of phrases. In some embodiments, each mapped word is associated with one or more other mapped words to provide the plurality of phrases. Associating mapped words includes concatenating word representations in some examples. Accordingly, a dimension of a phrase may be based on a number of word representations included in the phrase.
In some embodiments, each word of each sentence of the training data may be used as a center word of a phrase. A center word may be referred to as a word of interest in some instances. Further, each phrase may include context of the center word. Because each phrase provided at the block 815 may include a same amount of context, each of the phrases may have a same length. In some examples, each phrase may include left context, or word representations of words preceding the center word in a sentence, and right context, or word representations of words following the center word in a sentence. Phrases may include a same amount of left context and right context in some examples.
At block 820, the device encodes each of the plurality of phrases to provide a respective plurality of encoded phrases. Generally, each of the plurality of phrases may have a representation of a first type (e.g., a dimension of a first order) and each of the plurality of encoded phrases may have a representation of a second type different than the first type (e.g., a dimension of a second order different than the first order). Each of the encoded phrases may be projected into the same continuous space as the word and phrase representations.
In some embodiments, encoding a phrase includes adjusting a dimensionality of the phrase and/or reconstructing the phrase. Adjusting a dimensionality may include projecting (e.g., reducing) the phrase from the first dimension to the second dimension and reconstructing the phrase may include reconstructing the phrase in a manner such that a reconstruction error is minimized.
In some embodiments, encoding a phrase may include applying one or more weight factors of a first set of weight factors (e.g., weight matrix) to a phrase to adjust a dimensionality of the phrase and applying one or more weight factors of a second set of weight factors to reconstruct the phrase. The weight factors may be applied using an autoencoder and/or a neural network in some examples.
At block 825, the device determines a value for each of the plurality of encoded phrases. The value may comprise an indexing power of the phrase and/or may indicate a discriminative strength of a phrase in some examples. In some embodiments, the device determines a value for each phrase of each sentence of the training data.
In some embodiments, the device determines each value using a representation of each sentence. By way of example, for each sentence, the device may average all phrases of the sentence to provide a representation of the sentence. Averages provided in this manner are provided as centroids in some embodiments. The device then maps each of the centroids in the continuous space and clusters the centroids using one or more clustering algorithms. Such clustering algorithms include a hierarchical k-nearest-neighbor clustering algorithm, a k-means clustering algorithm (e.g., for coarse partitioning of clusters), a hierarchical clustering algorithm (e.g., for fine partitioning of clusters), or a combination thereof. Once centroids have been clustered, each phrase is compared to clusters in the continuous space to determine a respective value. In some embodiments, the comparison includes determining a number of times a center word of each phrase appears in each of the clusters and/or includes determining a normalized entropy for each center word of each phrase.
At block 830, the device identifies one or more phrases of the plurality of encoded phrases having a value exceeding a threshold. In some embodiments, phrases identified in this manner are provided as a set of parsimonious and/or discriminatory phrases that may be used in one or more natural language processing applications.
In accordance with some embodiments, FIG. 9 shows a functional block diagram of an electronic device 900 configured in accordance with the principles of the various described embodiments, including those described with reference to FIG. 8. The functional blocks of the device are, optionally, implemented by hardware, software, or a combination of hardware and software to carry out the principles of the various described embodiments. It is understood by persons of skill in the art that the functional blocks described in FIG. 9 are, optionally, combined or separated into sub-blocks to implement the principles of the various described embodiments. Therefore, the description herein optionally supports any possible combination or separation or further definition of the functional blocks described herein.
As shown in FIG. 9, an electronic device 900 includes a processing unit 902. In some embodiments, the processing unit 902 includes a receiving unit 904, a mapping unit 906, an associating unit 908, an encoding unit 910, a determining unit 912, an identifying unit 914, and optionally, an adjusting unit 916, a reconstructing unit 918, an applying unit 920, a minimizing unit 922, a providing unit 924, and a clustering unit 926.
In some embodiments, the processing unit 902 is configured to receive (e.g., with the receiving unit 904) a plurality of words; map (e.g., with the mapping unit 906) each of the plurality of words; associate (e.g., with the associating unit 908) the mapped words to provide a plurality of phrases, each of the plurality of phrases having a representation of a first type; encode (e.g., with the encoding unit 910) each of the plurality of phrases to provide a respective plurality of encoded phrases, each of the plurality of encoded phrases having a representation of a second type different than the first type; determine (e.g., with the determining unit 912) a value of each of the plurality of encoded phrases; and identify (e.g., with the identifying unit 914) one or more phrases of the plurality of encoded phrases having a value exceeding a threshold.
In some embodiments, mapping each of the plurality of words to a word representation includes mapping (e.g., with the mapping unit 906) a character sequence of each of the plurality of words.
In some embodiments, each of the plurality of phrases includes a same number of mapped words.
In some embodiments, encoding each of the plurality of phrases to provide a respective plurality of encoded phrases comprises: for each phrase, adjusting (e.g., with the adjusting unit 916) a dimensionality of the phrase and reconstructing (e.g., with the reconstructing unit 918) the projected phrase to provide an encoded phrase.
In some embodiments, adjusting a dimensionality of the phrase comprises applying (e.g., with the applying unit 920) a first weight matrix to the phrase and reconstructing (e.g., with the reconstructing unit 918) the phrase to provide an encoded phrase comprises applying a second weight matrix to the phrase.
In some embodiments, reconstructing the phrase to provide an encoded phrase comprises minimizing (e.g., with the minimizing unit 922) a reconstruction error.
In some embodiments, determining a value of each of the plurality of encoded phrases comprises providing (e.g., with the providing unit 924) a spatial representation of the plurality of phrases to provide a cluster; clustering (e.g., with the clustering unit 926) the spatial representation with another spatial representation; and determining (e.g., with the determining unit 912) the value of a word of each of the plurality of phrases based on the cluster.
In some embodiments, the processing is further configured to determine (e.g., with the determining unit 912) whether the value of the word of each of the plurality of phrases satisfies a threshold.
In some embodiments, clustering the spatial representation with another spatial representation to provide a cluster comprises clustering (e.g., with the clustering unit 926) with a hierarchical k-nearest-neighbor clustering algorithm.
In some embodiments, clustering the spatial representation with another spatial representation to provide a cluster comprises clustering (e.g., with the clustering unit 926) with at least one of a k-means clustering algorithm or a hierarchical clustering algorithm.
In some embodiments, the plurality of encoded phrases and the spatial representation are associated with a same vector space.
In some embodiments, a first word of the plurality of words and a second word of the plurality of words have a same character sequence.
The operation described above with respect to FIG. 8 is, optionally, implemented by components depicted in FIGS. 1A-B, 3, and 9. For example, receiving operation 805, mapping operation 810, associating operation 815, encoding operation 820, determining operation 825, and identifying operation 830 are optionally implemented by processor(s) 120. It would be clear to a person of ordinary skill in the art how other processes can be implemented based on the components depicted in FIGS. 1A-B, 3, and 9.
It is understood by persons of skill in the art that the functional blocks described in FIG. 9 are, optionally, combined or separated into sub-blocks to implement the principles of the various described embodiments. Therefore, the description herein optionally supports any possible combination or separation or further definition of the functional blocks described herein. For example, processing unit 902 can have an associated “controller” unit that is operatively coupled with processing unit 902 to enable operation. This controller unit is not separately illustrated in FIG. 9 but is understood to be within the grasp of one of ordinary skill in the art who is designing a device having a processing unit 902, such as device 900. As another example, one or more units, such as the receiving unit 904, may be hardware units outside of processing unit 902 in some embodiments. The description herein thus optionally supports combination, separation, and/or further definition of the functional blocks described herein.
Although the disclosure and examples have been fully described with reference to the accompanying figures, it is to be noted that various changes and modifications will becomeapparent to those skilled in the art. Such changes and modifications are to be understood as being included within the scope of the disclosure and examples as defined by the appended claims.