WO2014032265A1 - Modèle de langage de l'historique de navigation pour éditeur de procédés de saisie - Google Patents

Modèle de langage de l'historique de navigation pour éditeur de procédés de saisie Download PDF

Info

Publication number
WO2014032265A1
WO2014032265A1 PCT/CN2012/080815 CN2012080815W WO2014032265A1 WO 2014032265 A1 WO2014032265 A1 WO 2014032265A1 CN 2012080815 W CN2012080815 W CN 2012080815W WO 2014032265 A1 WO2014032265 A1 WO 2014032265A1
Authority
WO
WIPO (PCT)
Prior art keywords
character string
language model
latin character
browsing history
recited
Prior art date
Application number
PCT/CN2012/080815
Other languages
English (en)
Inventor
Mu Li
Xi Chen
Original Assignee
Microsoft Corporation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Microsoft Corporation filed Critical Microsoft Corporation
Priority to EP12883601.2A priority Critical patent/EP2891036A4/fr
Priority to CN201280075563.6A priority patent/CN104813257A/zh
Priority to PCT/CN2012/080815 priority patent/WO2014032265A1/fr
Priority to US14/423,950 priority patent/US20150199332A1/en
Publication of WO2014032265A1 publication Critical patent/WO2014032265A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/12—Use of codes for handling textual entities
    • G06F40/126—Character encoding
    • G06F40/129—Handling non-Latin characters, e.g. kana-to-kanji conversion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/274—Converting codes to words; Guess-ahead of partial word inputs

Definitions

  • This disclosure relates to the technical field of computer input.
  • An input method editor is a computer functionality that assists a user to input text into a host application of a computing device.
  • An IME may provide several suggested words and phrases based on received inputs from the user as candidates for insertion into the host application. For example, the user may input one or more initial characters of a word or phrase and an IME, based on the initial characters, may provide one or more suggested words or phrases for the user to select a desired one.
  • an IME may also assist the user to input non-Latin characters such as Chinese.
  • the user may input Latin characters through a keyboard.
  • the IME returns one or more Chinese characters as candidates for insertion. The user may then select the proper character and insert it.
  • the IME is useful for the user to input non-Latin characters using a Latin-character keyboard.
  • Some implementations provide techniques and arrangements for predicting a non-Latin character string based at least in part on a browsing history language model.
  • the browsing history language model may be generated based on browsing history information.
  • the browsing history information may include at least cached browsing content and may also include real-time browsing content.
  • the predicted non-Latin character string may be provided in response to receiving a Latin character string via an input method editor interface.
  • some examples may predict a Chinese character string based at least in part on the browsing history language model in response to receiving a Pinyin character string.
  • FIG. 1 illustrates an example system according to some implementations.
  • FIG. 2 illustrates an example input method editor interface according to some implementations.
  • FIG. 3 illustrates an example input method editor interface according to some implementations.
  • FIG. 4 illustrates an example process flow according to some implementations .
  • FIG. 5 illustrates an example process flow according to some implementations .
  • FIG. 6 illustrates an example system in which some implementations may operate.
  • Some examples include techniques and arrangements for implementing a browsing history language model with an input method editor (IME). For instance, it may be difficult for a user to input characters into a computer for a language that is based on non-Latin characters (e.g., the Chinese language). For example, there are thousands of Chinese characters, and a typical Western keyboard is limited to 26 letters.
  • the present disclosure relates to an IME that predicts a non-Latin character string in response to receiving a Latin character string from a user. The predicted non-Latin character string is based at least in part on a browsing history language model.
  • the IME may be used to translate Pinyin text (i.e., Chinese characters represented phonetically by Latin characters) into Chinese characters. It will be appreciated that the present disclosure is not limited to Chinese characters. For example, other illustrative non-Latin characters may include Japanese characters or Korean characters, among other alternatives.
  • a statistical language model may be used to compute a conversion probability of each possible conversion and may select the one with the highest probability for presentation to a user.
  • SLM statistical language model
  • a particular type of SLM referred to as an N-gram SLM, may decompose the probability of a string of consecutive words into the products of the conditional probabilities between two, three, or more consecutive words in the string.
  • An IME may be released with a language model for generic usage (i.e., a "general" language model), which is trained for most common typing scenarios.
  • a general language model may be inadequate for a particular user (e.g., a user with a particular browsing history). That is, different users may have different preferences, and an IME that utilizes a general language model may suggest a word or phrase that may be inappropriate for a particular user.
  • an IME that utilizes a general language model may suggest a first word or phrase (i.e., a first set of non-Latin characters).
  • the first word or phrase may have the same pronunciation as a second word or phrase (i.e., a second set of non- Latin characters).
  • the first word or phrase may be appropriate for a standard user but may be less appropriate for another user. Instead, the second word or phrase may be more appropriate for such a user.
  • Web browsing history is an important source of information about a user. For example, a user may browse content related to recent news events or may browse special topics that the user may be interested in. For example, a computer programmer may browse one or more portal sites for various news items and may also browse one or more software development sites. As such, the browsing history of the user may contain the latest general hot topics and texts related to programming skills, among other information.
  • the present disclosure describes an IME that utilizes a browsing history language model to predict a non-Latin character string that may be more appropriate for a user with a particular browsing history than a non-Latin character string that is predicted based on the general language model.
  • FIG. 1 illustrates an example framework of a system 100 according to some implementations.
  • the system 100 includes an input method editor (IME) application 102 that is communicatively coupled to a browsing history language model 104 and a general language model 106.
  • the system 100 further includes an adaptive language model builder 108 that is adapted to receive browsing history information 1 10.
  • the browsing history information 1 10 may include at least cached browsing content 1 12 stored at a browser cache 1 14.
  • An IME interface 1 16 may be provided to a user 1 18 via a computing device 120. While the computing device 120 is shown in FIG. 1 as separate from the above described components of the system 100, it will be appreciated that this is for illustrative purposes only. For instance, in some examples, all of the components of the system 100 may be included on the computing device 120, while in other examples, the components may be distributed across any number of computing devices able to communicate with one another, such as over one or more networks or other communication connections.
  • IME input method editor
  • the IME application 102 is configured to generate the IME interface 1 16 for display to the user 1 18 via the computing device 120.
  • the adaptive language model builder 108 is configured to generate the browsing history language model 104 based on the browsing history information 1 10.
  • the IME application 102 is further configured to receive a Latin character string 122 via the IME interface 1 16. In response to receiving the Latin character string 122, the IME application 102 is configured to predict a non-Latin character string 124 based at least in part on the browsing history language model 104.
  • the adaptive language model builder 108 may generate the browsing history language model 104 based on an analysis of the browsing history information 1 10.
  • the browsing history language model 104 may include an N-gram statistical language model.
  • Such an N-gram statistical language model may decompose the probability of a string of consecutive words into the products of the conditional probabilities between multiple (e.g., two, three, four, five, etc.) consecutive words in the string. Such analysis may be performed for each of the one or more files 1 12.
  • Some implementations provide a system service that may periodically monitor the browser cache 1 14 to determine whether new browsing content has been saved to the browser cache 1 14. In response to determining that new browsing content has been saved, the adaptive language model builder 108 may process the new browsing content to update the browsing history language model 104.
  • the browsing history information 1 10 may also include real-time browsing content 126, as shown in phantom.
  • a plug-in of a browser application 128 e.g., a web browser application
  • the adaptive language model builder 108 may process the real-time browsing content 126 to update the browsing history language model 104.
  • the plug-in of the browser application 128 may not provide real-time browsing information when a browsing mode is set to private browsing. That is, the browsing history information 1 10 may optionally only include the cached browsing content 1 12 that is stored at the browser cache.
  • the IME application 102 receives the Latin character string 122 via the IME interface 1 16.
  • the Latin character string 122 may include Pinyin text
  • the predicted non-Latin character string 124 may include one or more Chinese characters.
  • a plurality of non-Latin character strings may be associated with the Latin character string 122 received via the IME interface 1 16.
  • a conversion probability may be associated with each non-Latin character string of the plurality of non-Latin character strings.
  • the IME application 102 may predict the non- Latin character string 124 for display to the user 1 18 based at least in part on the browsing history language model 104. In a particular embodiment, the IME application 102 predicts the non-Latin character string 124 by identifying the non- Latin character string with a highest conversion probability.
  • the IME application 102 may order the plurality of non-Latin character strings based on the conversion probability and may display an ordered list of non-Latin character strings via the IME interface 1 16.
  • one or more predicted non-Latin character strings may be determined based on the browsing history language model 104 and the general language model 106.
  • C may represent the Chinese string to be predicted
  • P m (C) may represent a probability determined based on the general language model 106
  • P b (C) may represent a probability determined based on the browsing history language model 104.
  • the weighting factor ⁇ may include a default weighting factor. That is, the weighting factor can be "pre-tuned” to a weighting factor that has been previously verified as accurate in most cases.
  • the weighting factor may include a user-defined weighting factor. For example, the user-defined weighting factor may be received from the user 1 18, and the weighting factor may be modified from the default weighting factor to the user-defined weighting factor. This may allow the user 1 18 to "tune" the weighting factor according to personal preference.
  • the general language model 106 may identify a first non-Latin character string as the non-Latin character string with the highest conversion probability.
  • the browsing history language model 104 may identify a second non-Latin character string as the non-Latin character string with the highest conversion probability.
  • the first non-Latin character string identified by the general language model 106 may be different than the second non-Latin character string identified by the browsing history language model 104.
  • the Latin character string 122 received from the user 1 18 may be the Pinyin text "wan'shang'shi'shi.”
  • the browsing history language model 104 may predict that the Chinese character string 3 ⁇ 43 ⁇ 4_t ⁇ ⁇ (meaning "10 P.M.") is more appropriate for display than the Chinese character string 3 ⁇ 43 ⁇ 4_t3 ⁇ 43 ⁇ 4 (meaning "have a try in the evening") predicted by the general language model 106.
  • the Latin character string 122 received from the user 1 18 may be the Pinyin text "you'xiang'tu.”
  • the browsing history language model 104 may predict that the Chinese character string i3 ⁇ 4 S (meaning “directed graph”) may be more appropriate for display than the Chinese character string y&fjt
  • FIG. 1 illustrates that the non-Latin character string 124 displayed via the IME interface 1 16 may vary depending on whether the browsing history language model 104 identifies the non-Latin character string 124 as more appropriate for display based on the browsing history information 1 10.
  • FIG. 2 illustrates an example of an input method editor (IME) interface
  • FIG. 2 may correspond to the IME interface 1 16 of FIG. 1.
  • the IME interface 1 16 includes a Latin character string input window 202 and a non-Latin character string candidates window 204.
  • the Latin character string input window 202 is configured to receive a Latin character string (e.g., the Latin character string 122 of FIG. 1).
  • the non-Latin character string candidates window 204 is configured to display one or more non-Latin character string candidates.
  • FIG. 2 illustrates that a plurality of non-Latin (e.g., Chinese) character strings may be associated with the Latin character string received via the IME interface 1 16.
  • a conversion probability may be associated with each of the non- Latin character strings.
  • An IME application e.g., the IME application 102 of FIG. 1 may order the non-Latin character strings based on conversion probability and may display an ordered list of non-Latin character strings via the IME interface 1 16.
  • the Latin character string received via the Latin character string input window 202 may be the Pinyin text "wan'shang'shi'shi.”
  • the non-Latin character string candidates window 204 displays a first Chinese character string candidate 206 (i.e., 3 ⁇ 43 ⁇ 4_t ⁇ ⁇ ) and a second Chinese character string candidate 208 (i.e., 3 ⁇ 43 ⁇ 4_t3 ⁇ 43 ⁇ 4).
  • the browsing history language model 104 may identify the first Chinese character string candidate 206 (i.e., 3 ⁇ 43 ⁇ 4_t ⁇ ⁇ ) as the Chinese character string with a highest conversion probability.
  • the general language model 106 may identify the second Chinese character string candidate 208 (i.e., 3 ⁇ 43 ⁇ 4_t3 ⁇ 43 ⁇ 4) as the Chinese character string with a highest conversion probability.
  • the Chinese character string 3 ⁇ 43 ⁇ 4_t ⁇ ⁇ (meaning "10 P.M.") may be more appropriate for display than the Chinese character string 3 ⁇ 43 ⁇ 4_t3 ⁇ 43 ⁇ 4 (meaning "have a try in the evening") predicted by the general language model 106.
  • the first Chinese character string candidate 206 i.e., 3 ⁇ 43 ⁇ 4_t+ ⁇
  • the second Chinese character string candidate 208 i.e., 3 ⁇ 43 ⁇ 4_t3 ⁇ 43 ⁇ 4) predicted by the general language model 106.
  • the Chinese character string 3 ⁇ 43 ⁇ 4 _t ⁇ ⁇ may be presented as the first Chinese character string candidate 206 in the non-Latin character string candidates window 204.
  • 3 ⁇ 4 predicted by the general language model 106 is provided as the second Chinese character string candidate 208 in the non-Latin character string candidates window 204.
  • alternative non-Latin character string candidates may be presented.
  • alternative Chinese character strings predicted by the browsing history language model 104 may be presented.
  • alternative numbers of candidates may be displayed.
  • FIG. 3 illustrates the exemplary input method editor interface 1 16 after receiving a Latin character string input that is different than the Latin character string input of FIG. 2.
  • the Latin character string received via the Latin character string input window 202 may be the Pinyin text "you'xiang'tu.”
  • the non-Latin character string candidates window 204 displays a first Chinese character string candidate 302 (i.e., and a second Chinese character string candidate 304 (i.e., yt3 ⁇ 4 f H3).
  • the Chinese character string meaning
  • the Chinese character string i3 ⁇ 4 S may be presented as the first Chinese character string candidate 302 in the non-Latin character string candidates window 204.
  • 3 ⁇ 4 is provided as the second Chinese character string candidate 304 in the non-Latin character string candidates window 204.
  • alternative non-Latin character string candidates may be presented. Further, while only two candidates are illustrated in the non-Latin character string candidates window 204, alternative numbers of candidates may be displayed.
  • FIGS. 4 and 5 illustrate example process flows according to some implementations.
  • each block represents one or more operations that can be implemented in hardware, software, or a combination thereof.
  • the blocks represent computer- executable instructions that, when executed by one or more processors, cause the processors to perform the recited operations.
  • computer-executable instructions include routines, programs, objects, modules, components, data structures, and the like that perform particular functions or implement particular abstract data types.
  • the order in which the blocks are described is not intended to be construed as a limitation, and any number of the described operations can be combined in any order and/or in parallel to implement the processes. Numerous other variations will be apparent to those of skill in the art in light of the disclosure herein.
  • the process flows 400 and 500 are described with reference to the system 100, described above, although other models, frameworks, systems and environments may implement the illustrated process.
  • the process flow 400 includes generating a browsing history language model based on browsing history information.
  • the IME application 102 of FIG. 1 may generate the browsing history language model 104 based on the browsing history information 1 10.
  • an N-gram statistical language model may be employed to analyze the browsing history information 1 10.
  • the general language model 106 may identify a first non-Latin character string as the non-Latin character string with the highest conversion probability.
  • the browsing history language model 104 may identify a second non-Latin character string as the non-Latin character string with the highest conversion probability.
  • the second non-Latin character string predicted by the browsing history language model 104 may be different from the first non- Latin character string predicted by the general language model 106.
  • the content of the browsing history information 1 10 may affect a prediction of a non- Latin character string.
  • the predicted non-Latin character string may more accurately reflect the interests of the user 1 18.
  • a web browser plug-in may filter one or more web pages as the user is browsing in substantially real-time.
  • the plug-in may analyze the data, combine the data with the previous browsing history, and integrate the data into the browsing history language model 104.
  • An advantage of this approach is real-time processing capability, while it may require fast processing to avoid bringing noticeable latency to users.
  • a system service may periodically check one or more cache folders of one or more browsers and may examine the contents of the cache folders to build the browser history language model 104. This method may be able to examine the browsing history of multiple browsers but may not update the browser history language model 104 in substantially real-time.
  • a web browser plug-in may be responsible for detecting the content update, while a system service may be responsible for building the browser history language model 104.
  • the process flow 400 includes predicting a non-Latin character string based at least in part on the browsing history language model, in response to receiving a Latin character string via an IME interface.
  • the IME application 102 of FIG. 1 may predict the non-Latin character string 124 based at least in part on the browsing history language model 104, in response to receiving the Latin character string 122 via the IME interface 1 16.
  • a plurality of non-Latin character strings may be associated with the Latin character string 122 received via the IME interface 1 16. Multiple non-Latin character strings may be displayed as candidates for user selection. A conversion probability may be associated with each of the non-Latin character string candidates. The conversion probability may be used to determine the order in which the non-Latin character string candidates are displayed.
  • FIG. 2 illustrates an ordered list of non-Latin character strings displayed in response to the user 1 18 providing the Pinyin text "wan'shang'shi'shi" via the Latin character string input window 202.
  • the non- Latin character string candidates window 204 displays a first Chinese character string candidate 3 ⁇ 43 ⁇ 4_t ⁇ ⁇ and a second Chinese character string candidate B3 ⁇ 4_h3 ⁇ 4
  • the conversion probability associated with the first Chinese character string candidate 3 ⁇ 43 ⁇ 4 _b ⁇ H was determined to be higher than the conversion probability associated with the second Chinese character string candidate 3 ⁇ 43 ⁇ 4_t3 ⁇ 43 ⁇ 4.
  • the non-Latin character string candidates window 204 displays a first Chinese character string candidate i3 ⁇ 4 S and a second Chinese character string candidate yf3 ⁇ 4 f
  • the conversion probability associated with the first Chinese character string candidate i3 ⁇ 4 S was determined to be higher than the conversion probability associated with the second Chinese character string candidate [3 ⁇ 4
  • the predicted non-Latin character string 124 is determined based on the browsing history language model 104 and the general language model 106.
  • the first Chinese character string candidate (e.g., 3 ⁇ 43 ⁇ 4_t ⁇ ⁇ in FIG. 2 or in FIG. 3) may represent the non-
  • the second Chinese character string candidate (e.g., 3 ⁇ 43 ⁇ 4_t3 ⁇ 43 ⁇ 4 in FIG. 2 or y3 ⁇ 4ff
  • a contribution of the browsing history language model 104 may be determined based on a weighting factor.
  • the weighting factor may include a default weighting factor or a user-defined weighting factor.
  • the user 1 18 may adjust the weighting factor accordingly.
  • FIG. 5 illustrates another example process flow according to some implementations.
  • FIG. 5 illustrates that the browsing history language model may be updated based on new browsing content.
  • the process flow 500 includes generating a browsing history language model based on browsing history information.
  • the IME application 102 of FIG. 1 may generate the browsing history language model 104 based on the browsing history information 1 10.
  • the process flow 500 includes predicting a non-Latin character string based at least in part on the browsing history language model, in response to receiving a Latin character string via an input method editor interface.
  • the IME application 102 of FIG. 1 may predict the non-Latin character string 124 based at least in part on the browsing history language model 104, in response to receiving the Latin character string 122 via the IME interface 1 16.
  • the process flow 500 includes determining whether the browsing history information includes new browsing content. When it is determined that there is new browsing content, the process flow 500 may proceed to block 508. When new browsing content has not been detected, the process flow 500 returns to block 504.
  • the process flow 500 may include processing the new browsing content to update the browsing history language model.
  • a plug-in may detect new browsing content in substantially real-time. For example, referring to FIG. 1, a plug-in associated with the browser application 128 may provide the real-time browsing content 126, and the real-time browsing content 126 may be processed in substantially real-time to update the browsing history language model 104.
  • a system service may periodically monitor one or more browser cache locations to determine whether new browsing content has been saved. The new browsing content may then be processed to update the browsing history language model 104. For example, referring to FIG. 1 , a system service may periodically monitor the browser cache 1 14 for new browsing content and then process the new browsing content to update the browsing history language model 104.
  • predicting a non-Latin character string may be based at least in part on the updated browsing history language model.
  • a Latin character string may be received via the IME interface (e.g., the IME interface 1 16).
  • a non-Latin character string is predicted based at least in part on the updated browsing history language model.
  • the Latin character string received at block 510 may be the same as the Latin character string received at block 504.
  • the predicted non-Latin character string may or may not be the same. That is, the update to the browsing history language model may or may not affect the prediction of the non-Latin character string.
  • the browsing history language model prior to the update i.e., the browsing history language model generated at 502 may have predicted a particular non-Latin character string.
  • the updated browsing history language model i.e., after the update at block 508) may predict the same non-Latin character string or may predict a different non-Latin character string.
  • updating the browsing history language model may affect a prediction associated with one or more Latin character strings but may not affect a prediction associated with other Latin character strings.
  • FIG. 6 illustrates an example configuration of a computing device 600 and an environment that can be used to implement the modules and functions described herein.
  • the computing device 600 corresponds to the computing device 120 of FIG. 1 but it should be understood that the computing device 120 may be configured in a similar manner to that illustrated.
  • the computing device 600 may include at least one processor 602, a memory 604, communication interfaces 606, a display device 608 (e.g. a touchscreen display), other input/output (I/O) devices 610 (e.g. a touchscreen display or a mouse and keyboard), and one or more mass storage devices 612, able to communicate with each other, such as via a system bus 614 or other suitable connection.
  • I/O input/output
  • the processor 602 may be a single processing unit or a number of processing units, all of which may include single or multiple computing units or multiple cores.
  • the processor 602 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions.
  • the processor 602 can be configured to fetch and execute computer-readable instructions stored in the memory 604, mass storage devices 612, or other computer-readable media.
  • Memory 604 and mass storage devices 612 are examples of computer storage media for storing instructions which are executed by the processor 602 to perform the various functions described above.
  • memory 604 may generally include both volatile memory and non-volatile memory (e.g., RAM, ROM, or the like).
  • mass storage devices 612 may generally include hard disk drives, solid-state drives, removable media, including external and removable drives, memory cards, flash memory, floppy disks, optical disks (e.g., CD, DVD), a storage array, a network attached storage, a storage area network, or the like.
  • Both memory 604 and mass storage devices 612 may be collectively referred to as memory or computer storage media herein, and may be computer-readable media capable of storing computer-readable, processor-executable program instructions as computer program code that can be executed by the processor 602 as a particular machine configured for carrying out the operations and functions described in the implementations herein.
  • the computing device 600 may also include one or more communication interfaces 606 for exchanging data with other devices, such as via a network, direct connection, or the like, as discussed above.
  • the communication interfaces 606 can facilitate communications within a wide variety of networks and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet and the like.
  • Communication interfaces 606 can also provide communication with external storage (not shown), such as in a storage array, network attached storage, storage area network, or the like.
  • a display device 608 such as touchscreen display or other display device, may be included in some implementations.
  • the display device 608 may be configured to display the IME interface 116 as described above.
  • Other I/O devices 610 may be devices that receive various inputs from a user and provide various outputs to the user, and may include a touchscreen, such as a touchscreen display, a keyboard, a remote controller, a mouse, a printer, audio input/output devices, and so forth.
  • Memory 604 may include modules and components for execution by the computing device 600 according to the implementations discussed herein.
  • memory 604 includes the IME application 102 and the adaptive language model builder 108 as described above with regard to FIG. 1.
  • Memory 604 may further include one or more other modules 616, such as an operating system, drivers, application software, communication software, or the like.
  • Memory 604 may also include other data 618, such as data stored while performing the functions described above and data used by the other modules 616.
  • Memory 604 may also include other data and data structures described or alluded to herein.
  • memory 604 may include information that is used in the course of deriving and generating the browsing history language model 104 as described above.
  • module can represent program code (and/or declarative-type instructions) that performs specified tasks or operations when executed on a processing device or devices (e.g., CPUs or processors).
  • the program code can be stored in one or more computer-readable memory devices or other computer storage devices.
  • the IME application 102 and the adaptive language model builder 108 may be implemented using any form of computer- readable media that is accessible by computing device 600.
  • “computer-readable media” includes, at least, two types of computer-readable media, namely computer storage media and communications media.
  • Computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data.
  • Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non- transmission medium that can be used to store information for access by a computing device.
  • communication media may embody computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transmission mechanism.
  • a modulated data signal such as a carrier wave, or other transmission mechanism.
  • computer storage media does not include communication media.
  • this disclosure provides various example implementations, as described and as illustrated in the drawings. However, this disclosure is not limited to the implementations described and illustrated herein, but can extend to other implementations, as would be known or as would become known to those skilled in the art. Reference in the specification to "one implementation,” “this implementation,” “these implementations” or “some implementations” means that a particular feature, structure, or characteristic described is included in at least one implementation, and the appearances of these phrases in various places in the specification are not necessarily all referring to the same implementation.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)
  • Machine Translation (AREA)

Abstract

Quelques exemples peuvent consister à générer un modèle de langage de l'historique de navigation sur la base des informations d'historique de navigation. En outre, certaines mises en oeuvre peuvent consister à prévoir et à présenter une chaîne de caractères non latins au moins en partie sur la base du modèle de langage d'historique de navigation, par exemple, en réponse à la réception d'une chaîne de caractères latins via une interface d'éditeur de procédés de saisie.
PCT/CN2012/080815 2012-07-20 2012-08-31 Modèle de langage de l'historique de navigation pour éditeur de procédés de saisie WO2014032265A1 (fr)

Priority Applications (4)

Application Number Priority Date Filing Date Title
EP12883601.2A EP2891036A4 (fr) 2012-08-31 2012-08-31 Modèle de langage de l'historique de navigation pour éditeur de procédés de saisie
CN201280075563.6A CN104813257A (zh) 2012-08-31 2012-08-31 用于输入法编辑器的浏览历史语言模型
PCT/CN2012/080815 WO2014032265A1 (fr) 2012-08-31 2012-08-31 Modèle de langage de l'historique de navigation pour éditeur de procédés de saisie
US14/423,950 US20150199332A1 (en) 2012-07-20 2012-08-31 Browsing history language model for input method editor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2012/080815 WO2014032265A1 (fr) 2012-08-31 2012-08-31 Modèle de langage de l'historique de navigation pour éditeur de procédés de saisie

Publications (1)

Publication Number Publication Date
WO2014032265A1 true WO2014032265A1 (fr) 2014-03-06

Family

ID=50182376

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2012/080815 WO2014032265A1 (fr) 2012-07-20 2012-08-31 Modèle de langage de l'historique de navigation pour éditeur de procédés de saisie

Country Status (3)

Country Link
EP (1) EP2891036A4 (fr)
CN (1) CN104813257A (fr)
WO (1) WO2014032265A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140059058A1 (en) * 2012-08-24 2014-02-27 Microsoft Corporation Candidate generation for predictive input using input history
EP3171279A1 (fr) * 2015-11-23 2017-05-24 Xiaomi Inc. Procédé et dispositif pour le traitement d'entrée

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101876853A (zh) * 2009-04-29 2010-11-03 北京搜狗科技发展有限公司 拼音输入方法及装置
CN101995963A (zh) * 2010-11-19 2011-03-30 哈尔滨工业大学 词汇自适应中文输入方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7478033B2 (en) * 2004-03-16 2009-01-13 Google Inc. Systems and methods for translating Chinese pinyin to Chinese characters
US20080294982A1 (en) * 2007-05-21 2008-11-27 Microsoft Corporation Providing relevant text auto-completions

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101876853A (zh) * 2009-04-29 2010-11-03 北京搜狗科技发展有限公司 拼音输入方法及装置
CN101995963A (zh) * 2010-11-19 2011-03-30 哈尔滨工业大学 词汇自适应中文输入方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP2891036A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140059058A1 (en) * 2012-08-24 2014-02-27 Microsoft Corporation Candidate generation for predictive input using input history
US8918408B2 (en) * 2012-08-24 2014-12-23 Microsoft Corporation Candidate generation for predictive input using input history
EP3171279A1 (fr) * 2015-11-23 2017-05-24 Xiaomi Inc. Procédé et dispositif pour le traitement d'entrée
US10614154B2 (en) 2015-11-23 2020-04-07 Xiaomi Inc. Methods, devices, and computer-readable medium for predicting the intended input from a user of an application in an electronic device

Also Published As

Publication number Publication date
CN104813257A (zh) 2015-07-29
EP2891036A4 (fr) 2015-10-07
EP2891036A1 (fr) 2015-07-08

Similar Documents

Publication Publication Date Title
US9824085B2 (en) Personal language model for input method editor
CN104813275B (zh) 用于预测文本的方法和系统
CN104951099B (zh) 一种基于输入法的展示候选项的方法和装置
US8782549B2 (en) Incremental feature-based gesture-keyboard decoding
CN101669116A (zh) 用于生成亚洲语字符的识别体系结构
US8806384B2 (en) Keyboard gestures for character string replacement
CN104380284A (zh) 针对多种语言处理内容的语音合成
CN103370705A (zh) 用于便利文本输入的方法和系统
US20150199332A1 (en) Browsing history language model for input method editor
CN108701124A (zh) 预测接下来的字母并在图形键盘的键中显示它们
US11544467B2 (en) Systems and methods for identification of repetitive language in document using linguistic analysis and correction thereof
KR102440635B1 (ko) 음성 패킷 녹취 기능의 안내 방법, 장치, 기기 및 컴퓨터 저장 매체
US8972241B2 (en) Electronic device and method for a bidirectional context-based text disambiguation
EP2891036A1 (fr) Modèle de langage de l'historique de navigation pour éditeur de procédés de saisie
KR102074764B1 (ko) 모바일 기기의 입력 인터페이스 내에서 맞춤법 검사를 지원하는 방법 및 시스템
KR101645674B1 (ko) 자동완성 후보 단어 제공 방법 및 장치
KR102158544B1 (ko) 모바일 기기의 입력 인터페이스 내에서 맞춤법 검사를 지원하는 방법 및 시스템
US10222978B2 (en) Redefinition of a virtual keyboard layout with additional keyboard components based on received input
US10546061B2 (en) Predicting terms by using model chunks
US10528661B2 (en) Evaluating parse trees in linguistic analysis
CA2821787C (fr) Appareil electronique pour la desambiguisation bidirectionnelle de textes axee sur le contexte et methode connexe
EP2660728A1 (fr) Dispositif électronique et procédé de désambiguïsation de texte contextuelle bidirectionnel
JP2018054717A (ja) 音声認識結果作成装置、方法及びプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12883601

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 14423950

Country of ref document: US

Ref document number: 2012883601

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE