WO2016155144A1 - 翻译信息的提供方法及系统 - Google Patents

翻译信息的提供方法及系统 Download PDF

Info

Publication number
WO2016155144A1
WO2016155144A1 PCT/CN2015/083902 CN2015083902W WO2016155144A1 WO 2016155144 A1 WO2016155144 A1 WO 2016155144A1 CN 2015083902 W CN2015083902 W CN 2015083902W WO 2016155144 A1 WO2016155144 A1 WO 2016155144A1
Authority
WO
WIPO (PCT)
Prior art keywords
target language
language statement
current
statement
user
Prior art date
Application number
PCT/CN2015/083902
Other languages
English (en)
French (fr)
Inventor
王帆
和为
Original Assignee
百度在线网络技术（北京）有限公司
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 百度在线网络技术（北京）有限公司 filed Critical 百度在线网络技术（北京）有限公司
Priority to KR1020167031835A priority Critical patent/KR101863484B1/ko
Priority to EP15887111.1A priority patent/EP3142018A4/en
Priority to JP2017535674A priority patent/JP6517352B2/ja
Priority to US15/322,515 priority patent/US10176169B2/en
Publication of WO2016155144A1 publication Critical patent/WO2016155144A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/42—Data-driven translation
    • G06F40/49—Data-driven translation using very large corpora, e.g. the web
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/42—Data-driven translation
    • G06F40/47—Machine-assisted translation, e.g. using translation memory
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
    • G06F3/0482—Interaction with lists of selectable items, e.g. menus
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/51—Translation evaluation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/53—Processing of non-Latin text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Definitions

  • the present invention relates to the field of translation technologies, and in particular, to a method and system for providing translation information.
  • the current translation system only displays one translation result by default for the same source language statement (that is, the original text to be translated). This method of providing only one translation result will reduce the accuracy of translation.
  • the present invention aims to solve at least one of the technical problems in the related art to some extent.
  • the first aspect of the present invention is to provide a method for providing translation information, which provides a plurality of translation results of a complete sentence in a quick and convenient manner without having to re-select one by one like multiple candidates. Words or phrases, so that users can view more translation results, effectively improve the accuracy of translation, and improve user satisfaction.
  • An embodiment of the second aspect of the present invention is to provide a system for providing translation information.
  • a third aspect of the invention is directed to a storage medium.
  • An embodiment of the fourth aspect of the present invention is to provide a providing apparatus for translating information.
  • a method for providing translation information includes: S1: receiving a source language statement input by a user, and acquiring a current target language statement according to the source language statement; S2, at the current interface Displaying the current target language statement and a preset control; and S3, receiving an operation performed by the user on the preset control, acquiring another target language statement according to the operation, and displaying the another target on the current interface Language statement.
  • the obtained target language statement and the preset control are displayed on the current interface, and another target language statement is obtained according to the operation performed by the user on the preset control, and then displayed on the current interface.
  • Another target language statement which provides a variety of translation results for a complete sentence in a fast and convenient way, without having to re-select words or phrases one by one as many candidates, so that users can view more translation results.
  • the utility model can effectively improve the accuracy of the translation and improve the satisfaction of the user.
  • the embodiment can be applied to a small-screen terminal such as a mobile phone, and has strong practicability.
  • a system for providing translation information includes: a first obtaining module, configured to receive a source language statement input by a user, and obtain a current target language statement according to the source language statement; a module, configured to display the current target language statement and a preset control on the current interface; and switch the display module, configured to receive an operation performed by the user on the preset control, acquire another target language statement according to the operation, and The other target language statement is displayed on the current interface.
  • the translation information providing system displays the obtained current target language statement and the preset control on the current interface through the display module, and acquires another target language statement according to the operation performed by the user on the preset control by switching the display module. And then displaying the above-mentioned another target language statement in the above current interface, which realizes providing a plurality of translation results of a complete sentence in a fast and convenient manner, without reselecting words or phrases one by one like multiple candidates, thereby allowing The user can view more translation results, effectively improve the accuracy of translation, and improve user satisfaction.
  • the embodiment can be applied to small screen terminals such as mobile phones, and has strong practicability.
  • a storage medium of an embodiment of the third aspect of the present invention is configured to store an application for performing a method for providing translation information according to the first aspect of the present invention.
  • a device for providing translation information includes: one or more processors; a memory; one or more modules, wherein the one or more modules are stored in the memory, When executed by the one or more processors, the following operations are performed: S1, receiving a source language statement input by a user, and acquiring a current target language statement according to the source language statement; S2, displaying the current target language on a current interface a statement and a preset control; and S3, receiving an operation performed by the user on the preset control, acquiring another target language statement according to the operation, and displaying the another target language statement on the current interface.
  • FIG. 1 is a schematic diagram of multiple candidate results provided by the existing Google translation system.
  • FIG. 2 is a flow chart of a method of providing translation information according to an embodiment of the present invention.
  • FIG. 3 is a first schematic diagram of a translation interface according to an embodiment of the present invention.
  • FIG. 4 is a second schematic diagram of a translation interface according to an embodiment of the present invention.
  • FIG. 5 is a third schematic diagram of a translation interface according to an embodiment of the present invention.
  • FIG. 6 is a flow diagram of obtaining a set of target language statements in accordance with an embodiment of the present invention.
  • Figure 7 is a schematic diagram of a set of target language statements obtained using the method of Figure 6.
  • FIG. 8 is a schematic structural diagram of a system for providing translation information according to an embodiment of the present invention.
  • FIG. 2 is a flow chart of a method of providing translation information according to an embodiment of the present invention.
  • the method for providing translation information includes:
  • S1 Receive a source language statement input by the user, and obtain a current target language statement according to the source language statement.
  • the translation system can receive the source language statement input by the user on the translation interface, and can obtain the corresponding target language statement according to the source language statement input by the user. In order to distinguish from other target language statements, the translation system will obtain The target language statement to is called the current target language statement.
  • the above source language statement can be "How do you feel recently?” and the current target language statement can be "How do you feel about the recent.”
  • the method further includes: acquiring a target language sentence set related to the current target language statement, wherein the target language sentence set stores a target language statement sorted according to a high to low confidence level.
  • the target language sentence set related to the target language statement "How do you feel about the recent” contains “How do you feel about recently”, “What do you feel about the recent”, “How do you feel about the recent” , “How do you like the recent” and other target language statements, and the confidence of these target language statements are ranked from high to low.
  • the current target language statement may be displayed on the corresponding translation interface.
  • a preset control may be displayed, where Preset controls include, but are not limited to, buttons.
  • the preset control may include a first button and a second button, wherein the first button may be used to view the next translation result, that is, the next target language statement is viewed; and the second button may be used to view the previous translation result. , that is, view the previous target language statement.
  • the corresponding button can be represented by a preset icon.
  • a button of "View the next translation result” can be indicated by “>”, and " ⁇ ” is used to indicate "View the previous one. Translation results” button.
  • the receiving the operation performed by the user on the preset control, and acquiring another target language statement according to the foregoing operation may be: receiving a trigger operation performed by the user on the first button, and Obtaining a next target language statement from the target language sentence set according to the triggering operation and the target language statement displayed on the current interface; or: receiving a trigger operation performed by the user on the second button, and according to the triggering operation and the current interface
  • the displayed target language statement retrieves the previous target language statement from the set of target language statements.
  • a button with the first button “Viewing the next translation result” is displayed, and the user can see more translation results after clicking the button.
  • the second button that is, the button of “viewing the previous translation result” may also be displayed on the translation interface, and the user clicks this button to return to view the previous translation result.
  • the embodiment of the present invention can be applied not only to a PC but also to a small-screen terminal such as a mobile phone.
  • the translation interface displayed on the mobile phone can be as shown in FIG. 5 . It should be noted that FIG. 5 is only an example. Generally, the translation interface displayed on the mobile phone may have a button of “viewing the previous translation result” in addition to the button of “viewing the next translation result”.
  • the foregoing embodiment of the method for providing translation information displays the obtained target language statement and the preset control in the current interface, and acquires another target language statement according to the operation performed by the user on the preset control, and then displays another target on the current interface.
  • Language statements which provide a variety of translation results for a complete sentence in a fast and convenient way, without having to re-select words or phrases one by one as many candidates, so that users can view more translation results, effectively The accuracy of the translation is improved, and the satisfaction of the user is improved.
  • the embodiment can be applied to a small-screen terminal such as a mobile phone, and has high practicability.
  • FIG. 6 is a flow diagram of obtaining a set of target language statements in accordance with an embodiment of the present invention.
  • obtaining a set of target language statements related to the current target language statement includes:
  • S601 Obtain a phrase segment of a current target language sentence, and obtain a candidate segment of each phrase segment to construct A set of candidate fragments.
  • S ij represents the jth candidate segment of the i-th phrase segment. Since S 11 , S 21 , and S 31 are the same as S 1 , S 2 , and S 3 , the current candidate segment set includes only S 12 , S 22 . , S 23 , S 32 , S 33 .
  • the confidence degree of each candidate segment can be calculated using a confidence calculation formula, wherein the confidence calculation formula is:
  • S represents the current target language statement
  • S ij represents the jth candidate segment of the i-th phrase segment
  • F k and ⁇ k represent the k-th feature and its weight
  • k is a positive integer.
  • translation model features and language model features two different types can be used: translation model features and language model features, wherein the translation model is used to describe the source language statement and the target language statement (or a phrase segment and the current target language statement in the source language statement).
  • the degree of translation of a phrase segment), the language model used to describe the fluency of the translation results it should be noted that the translation model features and language model features are used here, only examples.
  • ⁇ 1 and ⁇ 2 are dynamically adjustable feature weights, and the valid range of values is (-10.0, 10.0).
  • the calculation method of the translation model features is:
  • T(S) represents the translation model total score of the source speech sentence input by the user into the current target language sentence S
  • T(S i ) represents the translation model score of the S i segment generated from the source speech sentence input by the user
  • T ( S ij ) represents a translation model score for generating a S ij segment from a source speech sentence input by the user.
  • the calculation method of the language model feature is:
  • L(S) represents the language model total score of the current target language sentence S
  • L(S i ) represents the language model score of the S i segment
  • L(S ij ) represents the language model score of the S ij segment.
  • the scores of S 12 , S 22 , S 23 , S 32 , and S 33 are calculated using the confidence calculation formula, and if ⁇ 1 and ⁇ 2 are 0.8 and 0.2, respectively, S 12 is calculated.
  • the scores of S 22 , S 23 , S 32 , and S 33 are sorted in descending order of the scores, and the calculated scores, that is, the order of confidence from high to low are: S 32 , S 12 , S 22 , S 23 , ....
  • S603 Select a first candidate segment from the current candidate segment set to replace the corresponding phrase segment to generate a target language statement in the target language sentence set, and save the corresponding target language statement and the current candidate according to the generated sequence.
  • the selected candidate segment is deleted from the segment set until the current candidate segment set is empty.
  • phrase segment can be replaced in order to reduce the search space and prevent translation escaping (while replacing multiple phrase segments, which may result in a large deviation between sentence semantics and user input).
  • phrase segments may be replaced as needed.
  • the sentences can be arranged by automatically calculating the confidence without the user coming from the main selection, and the generated sentences are hidden in the background, when the user triggers the first button or the second button,
  • the corresponding target language statement can be obtained from the background and displayed on the front end, thus providing conditions for realizing multiple translation results of providing a complete sentence in a fast and convenient manner, thereby allowing the user to view more translation results, effectively Improve the accuracy of translation and improve user satisfaction.
  • the present invention also proposes a system for providing translation information.
  • FIG. 8 is a schematic structural diagram of a system for providing translation information according to an embodiment of the present invention.
  • the translation information providing system includes a first obtaining module 81, a display module 82, and a switching display module 83, wherein:
  • the first obtaining module 81 is configured to receive a source language statement input by the user, and obtain a current target language statement according to the source language statement; the display module 82 is configured to display the current target language statement and the preset control on the current interface; and switch the display module 83. And configured to receive an operation performed by the user on the preset control, obtain another target language statement according to the foregoing operation, and display the another target language statement on the current interface.
  • the first obtaining module 81 can receive the source language statement input by the user on the translation interface, and can obtain the corresponding target language statement according to the source language statement input by the user, in order to distinguish from other target language statements,
  • the target language statement obtained is referred to as the current target language statement.
  • the above source language statement can be "How do you feel recently?” and the current target language statement can be "How do you feel about the recent.”
  • the system may further include a second obtaining module 84, where the second obtaining module 84 may be configured to: acquire a target language sentence set related to the current target language statement, where the target language sentence set is saved according to a confidence level High to low target language statements for sorting.
  • the foregoing second obtaining module 84 includes a segment obtaining unit 841, a calculating sorting unit 842, and a sentence obtaining unit 843, wherein: the segment obtaining unit 841 is configured to acquire a phrase segment of the current target language sentence, and acquire each phrase segment.
  • Candidate segments to form a candidate segment set is configured to calculate a confidence level of each candidate segment in the candidate segment set, and sort all candidate segments according to a high to low confidence order; the statement obtaining unit 843 And each time, selecting a first candidate segment from the current candidate segment set to replace the corresponding phrase segment to generate a target language statement in the target language sentence set, and saving the corresponding target language statement according to the generated sequence and from the current The selected candidate segments are deleted from the candidate segment set until the current candidate segment set is empty.
  • the calculation sorting unit 842 is specifically configured to: calculate a confidence level of each candidate segment by using a confidence calculation formula, where the above-mentioned confidence calculation formula and a specific implementation process can be referred to the embodiment shown in FIG. Do not repeat them.
  • the target language sentence set related to the target language statement "How do you feel about the recent" acquired by the second obtaining module 84 stores "How do you feel about recently” and "What do you feel”. "about the recent”, “How do you feel the recent”, “How do you like the recent” and other target language statements, and the confidence of these target language statements are ranked from high to low.
  • the display module 82 can display the current target language statement on the corresponding translation interface, and in addition, the current target language statement can be displayed on the translation interface.
  • a preset control can be displayed, wherein the preset controls include, but are not limited to, buttons.
  • the preset control may include a first button and a second button, wherein the first button may be used to view the next button One translation result is to view the next target language statement; the second button can be used to view the previous translation result, that is, to view the previous target language statement.
  • the corresponding button can be represented by a preset icon.
  • a button of "View the next translation result” can be indicated by “>”, and " ⁇ ” is used to indicate "View the previous one. Translation results” button.
  • the switching display module is configured to: receive a trigger operation performed by the user on the first button, and according to the trigger operation and the target language statement displayed on the current interface Obtaining a next target language statement in the target language sentence set; and receiving a trigger operation performed by the user on the second button, and acquiring the target language sentence set from the target language statement according to the trigger operation and the target language statement displayed on the current interface A target language statement.
  • a button with the first button “Viewing the next translation result” is displayed, and the user can see more translation results after clicking the button.
  • the second button that is, the button of “viewing the previous translation result” may also be displayed on the translation interface, and the user clicks this button to return to view the previous translation result.
  • the embodiment of the present invention can be applied not only to a PC but also to a small-screen terminal such as a mobile phone.
  • the translation interface displayed on the mobile phone can be as shown in FIG. 5 . It should be noted that FIG. 5 is only an example. Generally, the translation interface displayed on the mobile phone may have a button of “viewing the previous translation result” in addition to the button of “viewing the next translation result”.
  • the system for providing the translation information described above displays the obtained current target language statement and the preset control on the current interface through the display module, and obtains another target language statement according to the operation performed by the user on the preset control by switching the display module, and then
  • the above current interface displays the other target language statement described above, and realizes providing a plurality of translation results of a complete sentence in a fast and convenient manner, without reselecting words or phrases one by one as many candidates, so that the user can view More translation results can effectively improve the accuracy of translation and improve user satisfaction.
  • the embodiment can be applied to small screen terminals such as mobile phones, and has strong practicability.
  • the present invention also provides a storage medium for storing an application for performing a method for providing translation information according to any of the embodiments of the present invention.
  • the present invention also provides a device for providing translation information, including: one or more processors; a memory; one or more modules, one or more modules stored in the memory, when being one or When multiple processors are executing, do the following:
  • S2' displays the current target language statement and preset controls on the current interface.
  • first and second are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
  • features defining “first” or “second” may include at least one of the features, either explicitly or implicitly.
  • the meaning of "a plurality” is at least two, such as two, three, etc., unless specifically defined otherwise.
  • a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
  • computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
  • the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.
  • portions of the invention may be implemented in hardware, software, firmware or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • the following techniques known in the art can be used. Any one of them or a combination thereof: a discrete logic circuit having logic gates for implementing logic functions on data signals, an application specific integrated circuit with suitable combination logic gates, a programmable gate array (PGA), Field programmable gate array (FPGA), etc.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Abstract

一种翻译信息的提供方法及系统，其中，翻译信息的提供方法包括：S1、接收用户输入的源语言语句，并根据源语言语句获取当前目标语言语句；S2、在当前界面显示当前目标语言语句和预设控件；以及S3、接收用户对预设控件执行的操作，根据操作获取另一目标语言语句，并在当前界面显示另一目标语言语句。实现了通过快速、便捷的方式来提供一个完整句子的多种翻译结果，而无需像多候选项一样一个个重新选择单词或词组，从而让用户可以查看更多的翻译结果，有效地提高翻译的准确率，提升用户的满意度，另外，还可以应用于手机等小屏幕终端，实用性强。

Description

翻译信息的提供方法及系统
相关申请的交叉引用
本申请要求百度在线网络技术(北京)有限公司于2015年03月27提交的、发明名称为“翻译信息的提供方法及系统”的、中国专利申请号“201510142606.3”的优先权。
技术领域
本发明涉及翻译技术领域，尤其涉及一种翻译信息的提供方法及系统。
背景技术
目前的翻译系统对于同一条源语言语句(即需要翻译的原文)，只默认展示一条翻译结果，这种只提供一个翻译结果的方式，会降低翻译的准确率。
为了解决翻译结果单一的问题，目前很多翻译系统都提供了翻译结果多候选机制，这样，当用户对当前翻译结果不满意时，可以自己选择单词或词组级别的候选结果，例如用户可以在如图1所示的谷歌(google)翻译系统中点击对应的单词或词组，并选择候选项中的单词，以获得其他翻译结果。
虽然现有的很多翻译系统都提供了翻译结果多候选机制，但如果一句话中的多个单词或词组都提供了候选项，对于翻译基础不好的用户而言，则无法判断选择哪个候选结果更好，无从选择；同时，这种方式需要用户一个个来选择候选结果，而无法通过便捷的方式来提供一个完整的句子的翻译结果。另外，多候选的功能隐藏较深，需要用户自己点击相应的单词或词组，才能给出该相应单词或词组对应的多候选结果，进一步地，由于手机界面较小，尤其不适合这种多候选的结果的展示。
发明内容
本发明旨在至少在一定程度上解决相关技术中的技术问题之一。为此，本发明第一方面实施例在于提出一种翻译信息的提供方法，该方法通过快速、便捷的方式来提供一个完整句子的多种翻译结果，而无需像多候选项一样一个个重新选择单词或词组，从而让用户可以查看更多的翻译结果，有效地提高翻译的准确率，提升用户的满意度。
本发明的第二方面实施例在于提出一种翻译信息的提供系统。
本发明的第三方面实施例在于提出一种存储介质。
本发明的第四方面实施例在于提出一种翻译信息的提供设备。
为了实现上述目的，本发明第一方面实施例的导翻译信息的提供方法，包括：S1、接收用户输入的源语言语句，并根据所述源语言语句获取当前目标语言语句；S2、在当前界面显示所述当前目标语言语句和预设控件；以及S3、接收用户对所述预设控件执行的操作，根据所述操作获取另一目标语言语句，并在所述当前界面显示所述另一目标语言语句。
根据本发明实施例的翻译信息的提供方法，通过在当前界面显示获得的当前目标语言语句和预设控件，并根据用户对预设控件执行的操作获取另一目标语言语句，然后在当前界面显示另一目标语言语句，实现了通过快速、便捷的方式来提供一个完整句子的多种翻译结果，而无需像多候选项一样一个个重新选择单词或词组，从而让用户可以查看更多的翻译结果，有效地提高翻译的准确率，提升用户的满意度，另外，该实施例可以应用于手机等小屏幕终端，实用性强。
为了实现上述目的，本发明第二方面实施例的翻译信息的提供系统，包括：第一获取模块，用于接收用户输入的源语言语句，并根据所述源语言语句获取当前目标语言语句；显示模块，用于在当前界面显示所述当前目标语言语句和预设控件；以及切换显示模块，用于接收用户对所述预设控件执行的操作，根据所述操作获取另一目标语言语句，并在所述当前界面显示所述另一目标语言语句。
根据本发明实施例的翻译信息的提供系统,通过显示模块在当前界面显示获得的当前目标语言语句和预设控件，并通过切换显示模块根据用户对预设控件执行的操作获取另一目标语言语句，然后在上述当前界面显示上述另一目标语言语句，实现了通过快速、便捷的方式来提供一个完整句子的多种翻译结果，而无需像多候选项一样一个个重新选择单词或词组，从而让用户可以查看更多的翻译结果，有效地提高翻译的准确率，提升用户的满意度，另外，该实施例可以应用于手机等小屏幕终端，实用性强。
为了实现上述目的，本发明第三方面实施例的存储介质，用于存储应用程序，所述应用程序用于执行本发明第一方面实施例所述的翻译信息的提供方法。
为了实现上述目的，本发明第四方面实施例的翻译信息的提供设备，包括：一个或者多个处理器；存储器；一个或者多个模块，所述一个或者多个模块存储在所述存储器中，当被所述一个或者多个处理器执行时进行如下操作：S1、接收用户输入的源语言语句，并根据所述源语言语句获取当前目标语言语句；S2、在当前界面显示所述当前目标语言语句和预设控件；以及S3、接收用户对所述预设控件执行的操作，根据所述操作获取另一目标语言语句，并在所述当前界面显示所述另一目标语言语句。
附图说明
图1是现有谷歌翻译系统提供的多候选结果示意图。
图2是本发明一个实施例的翻译信息的提供方法的流程图。
图3是本发明一个实施例的翻译界面示意图一。
图4是本发明一个实施例的翻译界面示意图二。
图5是本发明一个实施例的翻译界面示意图三。
图6是本发明一个实施例的获取目标语言语句集合的流程图。
图7是采用图6所示方法获取的目标语言语句集合的示意图。
图8是本发明一个实施例的翻译信息的提供系统的结构示意图。
具体实施方式
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本发明，而不能理解为对本发明的限制。
下面参考附图描述本发明实施例的翻译信息的提供方法及系统。
图2是本发明一个实施例的翻译信息的提供方法的流程图。
如图2所示，该翻译信息的提供方法包括：
S1、接收用户输入的源语言语句，并根据源语言语句获取当前目标语言语句。
在该实施例中，翻译系统可接收用户在翻译界面上输入的源语言语句，并可根据用户输入的源语言语句获取对应的目标语言语句，为了与其他目标语言语句进行区分，此处将获取到的目标语言语句称为当前目标语言语句。
例如，上述源语言语句可以为“你最近感觉怎么样”，当前目标语言语句可以为“How do you feel about the recent”。
另外，在该实施例中，还可以包括：获取与当前目标语言语句相关的目标语言语句集合，其中，该目标语言语句集合中保存有按照置信度由高到低进行排序的目标语言语句。
例如，与目标语言语句“How do you feel about the recent”相关的目标语言语句集合中保存有“How do you feel about recently”、“What do you feel about the recent”、“How do you feel the recent”、“How do you like the recent”等多个目标语言语句，且这些目标语言语句的置信度由高到低排列。
S2、在当前界面显示当前目标语言语句和预设控件。
在该实施例中，在获得当前目标语言语句后，可以在对应的翻译界面上显示当前目标语言语句，另外，除了可以在翻译界面显示当前目标语言语句外，还可以显示预设控件，其中， 预设控件包括但不限于按钮。
具体地，上述预设控件可以包括第一按钮和第二按钮，其中，第一按钮可以用于查看下一条翻译结果，即查看下一目标语言语句；第二按钮可以用于查看上一条翻译结果，即查看上一目标语言语句。
另外，为了方便用户区分两个按钮的功能，可以以预设图标来表示对应的按钮，例如，可以用“＞”表示“查看下一条翻译结果”的按钮，用“＜”表示“查看上一条翻译结果”的按钮。
S3、接收用户对预设控件执行的操作，根据上述操作获取另一目标语言语句，并在当前界面显示另一目标语言语句。
当预设控件包括第一按钮和第二按钮时，上述接收用户对预设控件执行的操作，根据上述操作获取另一目标语言语句，可以为：接收用户对第一按钮执行的触发操作，并根据上述触发操作和当前界面上显示的目标语言语句从目标语言语句集合中获取下一目标语言语句；也可以为：接收用户对第二按钮执行的触发操作，并根据上述触发操作和当前界面上显示的目标语言语句从目标语言语句集合中获取上一目标语言语句。
例如，在图3所示的翻译界面上显示有第一按钮即“查看下一条翻译结果”的按钮，用户在点击该按钮后可以看到更多的翻译结果。另外，如图4所示，翻译界面上也可以显示第二按钮即“查看上一条翻译结果”的按钮，用户点击此按钮可以返回查看上一条翻译结果。
另外，本发明实施例不仅可以应用在PC机上，也可以应用到手机等小屏幕终端上，其中，手机上显示的翻译界面可以如图5所示。需要说明的是，图5仅为一个示例，通常手机上显示的翻译界面除了“查看下一条翻译结果”的按钮外，还可以具有“查看上一条翻译结果”的按钮。
上述翻译信息的提供方法实施例，通过在当前界面显示获得的当前目标语言语句和预设控件，并根据用户对预设控件执行的操作获取另一目标语言语句，然后在当前界面显示另一目标语言语句，实现了通过快速、便捷的方式来提供一个完整句子的多种翻译结果，而无需像多候选项一样一个个重新选择单词或词组，从而让用户可以查看更多的翻译结果，有效地提高翻译的准确率，提升用户的满意度，另外，该实施例可以应用于手机等小屏幕终端，实用性强。
图6是本发明一个实施例的获取目标语言语句集合的流程图。
如图6所示，获取与当前目标语言语句相关的目标语言语句集合包括：
S601，获取当前目标语言语句的短语片段，并获取每个短语片段的候选片段，以构 成候选片段集合。
需要说明的是，在目前主流的基于统计的翻译系统(例如Google翻译系统、百度翻译系统)中，一旦翻译系统生成了译文，那么译文的短语划分方式也就确定了。
例如,对于当前目标语言语句S为“How do you feel about the recent”,百度翻译系统给出的短语片段Si为：(S1:How do)(S2:you feel about)(S3:the recent)，则上述短语片段及其对应的候选片段如表1所示。
表1 短语片段及其对应的候选片段
S1:How do S2:you feel about S3:the recent
S11:How do S21:you feel about S31:the recent
S12:What do S22:you feel S32:recently
  S23:you like S33:recent
其中，Sij表示第i个短语片段的第j个候选片段，由于S11,S21,S31与S1,S2,S3相同，故当前候选片段集合中仅包含S12，S22，S23，S32，S33。
S602，计算候选片段集合中每个候选片段的置信度，并按照置信度由高到低的顺序对所有候选片段进行排序。
在本实施例中，可以使用置信度计算公式计算每个候选片段的置信度，其中，置信度计算公式为：
Figure PCTCN2015083902-appb-000001
其中，S表示所述当前目标语言语句，Sij表示第i个短语片段的第j个候选片段，Fk和λk表示第k个特征及其权重，k为正整数。
具体地，可使用两种不同类型的特征：即翻译模型特征和语言模型特征，其中，翻译模型用来描述源语言语句与目标语言语句(或源语言语句中某个短语片段与当前目标语言语句中某个短语片段)的互译程度，语言模型用来描述翻译结果的流利程度，需要说明的是，此处使用翻译模型特征和语言模型特征，仅为示例。
假设用F1和λ1表示翻译模型特征及其权重，用F2和λ2表示语言模型特征及其权重，则原公式可以展开为：
Score(Sij,S)＝exp[λ1F1(Sij,S)+λ2F2(Sij,S)]
其中，λ1和λ2是可动态调整的特征权重，一般情况下有效的取值范围为(-10.0,10.0)。
其中，翻译模型特征的计算方法是：
F1(Sij,S)＝T(S)-T(Si)+T(Sij)
其中，T(S)表示用户输入的源语音语句翻译成当前目标语言语句S的翻译模型总得分， T(Si)表示从用户输入的源语音语句生成Si片段的翻译模型得分，T(Sij)表示从用户输入的源语音语句生成Sij片段的翻译模型得分。
语言模型特征的计算方法是：
F2(Sij,S)＝L(S)-L(Si)+L(Sij)
其中，L(S)表示当前目标语言语句S的语言模型总得分，L(Si)表示Si片段的语言模型得分，L(Sij)表示从Sij片段的语言模型得分。
关于翻译模型和语言模型的具体计算方法，可以参考《统计机器翻译》91页5.2.5节和121页7.1节。其中，《统计机器翻译》，为Philipp Koehn著，宗成庆张霄军译，电子工业出版社，2012年9月出版，ISBN:9787121175923。
在确定置信度计算公式后，使用置信度计算公式计算S12，S22，S23，S32，S33的得分,假设λ1和λ2分别是0.8和0.2，则在计算出S12，S22，S23，S32，S33的得分后，按照得分由高到低的顺序进行排序，假设计算出的得分即置信度由高到低的顺序为：S32,S12,S22,S23,……。
S603，每次从当前候选片段集合中选取首个候选片段替换对应的短语片段，以生成目标语言语句集合中的一个目标语言语句，并按照生成的先后顺序保存对应的目标语言语句和从当前候选片段集合中删除被选取的候选片段，直至当前候选片段集合为空。
由于当前候选片段集合中首个候选片段为S32，故使用S32替换S3，并按照生成的先后顺序保存生成的目标语言语句，然后从候选片段集合中删除S32，重复执行上述操作，即又使用S12替换S1，并按照生成的先后顺序保存生成的目标语言语句；然后使用S22替换S2，并按照生成的先后顺序保存生成的目标语言语句；再使用S23替换S2，并按照生成的先后顺序保存生成的目标语言语句，等等，最终目标语言语句集合中保存的目标语言语句如图7所示，其中置信度较高的句子在前，置信度较低的句子在后。
需要说明的是，在该实施例中之所以只能替换一个短语片段，是为了降低搜索空间和防止译文转义(同时替换多个短语片段，可能会导致句子语义与用户输入有较大的偏差)。当然，本领域的技术人员均理解，上述替换方式仅为一种示例，也可以根据需要替换多个短语片段。
由此可见，该实施例中，可以通过自动计算置信度来将句子进行排列，而无需用户来自主选择，并将生成的句子隐藏在后台，当用户触发第一按钮或第二按钮时，便可以从后台获取到对应的目标语言语句，并显示在前端，从而为实现以快速、便捷的方式提供一个完整句子的多种翻译结果提供了条件，进而让用户可以查看更多的翻译结果，有效地提高翻译的准确率，提升用户的满意度。
为了实现上述实施例，本发明还提出一种翻译信息的提供系统。
图8是本发明一个实施例的翻译信息的提供系统的结构示意图。
如图8所示，翻译信息的提供系统包括第一获取模块81、显示模块82和切换显示模块83，其中：
第一获取模块81用于接收用户输入的源语言语句，并根据上述源语言语句获取当前目标语言语句；显示模块82用于在当前界面显示上述当前目标语言语句和预设控件；切换显示模块83用于接收用户对上述预设控件执行的操作，根据上述操作获取另一目标语言语句，并在上述当前界面显示上述另一目标语言语句。
在该实施例中，第一获取模块81可接收用户在翻译界面上输入的源语言语句，并可根据用户输入的源语言语句获取对应的目标语言语句，为了与其他目标语言语句进行区分，此处将获取到的目标语言语句称为当前目标语言语句。
例如，上述源语言语句可以为“你最近感觉怎么样”，当前目标语言语句可以为“How do you feel about the recent”。
另外，该系统还可以包括第二获取模块84，第二获取模块84可以用于：获取与上述当前目标语言语句相关的目标语言语句集合，其中，上述目标语言语句集合中保存有按照置信度由高到低进行排序的目标语言语句。具体地，上述第二获取模块84包括片段获取单元841、计算排序单元842和语句获取单元843，其中：片段获取单元841用于获取上述当前目标语言语句的短语片段，并获取每个短语片段的候选片段，以构成候选片段集合；计算排序单元842用于计算上述候选片段集合中每个候选片段的置信度，并按照置信度由高到低的顺序对所有候选片段进行排序；语句获取单元843用于每次从当前候选片段集合中选取首个候选片段替换对应的短语片段，以生成上述目标语言语句集合中的一个目标语言语句，并按照生成的先后顺序保存对应的目标语言语句和从当前候选片段集合中删除被选取的候选片段，直至当前候选片段集合为空。
具体地，上述计算排序单元842具体用于：使用置信度计算公式计算每个候选片段的置信度，其中，上述置信度计算公式及具体的实现过程可参见图6所示的实施例，此处不赘述。从图7可以看出，第二获取模块84获取的与目标语言语句“How do you feel about the recent”相关的目标语言语句集合中保存有“How do you feel about recently”、“What do you feel about the recent”、“How do you feel the recent”、“How do you like the recent”等多个目标语言语句，且这些目标语言语句的置信度由高到低排列。
在该实施例中，在第一获取模块81获得当前目标语言语句后，显示模块82可以在对应的翻译界面上显示当前目标语言语句，另外，除了可以在翻译界面显示当前目标语言语句外，还可以显示预设控件，其中，预设控件包括但不限于按钮。
具体地，上述预设控件可以包括第一按钮和第二按钮，其中，第一按钮可以用于查看下 一条翻译结果，即查看下一目标语言语句；第二按钮可以用于查看上一条翻译结果，即查看上一目标语言语句。
另外，为了方便用户区分两个按钮的功能，可以以预设图标来表示对应的按钮，例如，可以用“＞”表示“查看下一条翻译结果”的按钮，用“＜”表示“查看上一条翻译结果”的按钮。
当预设控件包括第一按钮和第二按钮时，上述切换显示模块，具体用于：接收用户对上述第一按钮执行的触发操作，并根据上述触发操作和当前界面上显示的目标语言语句从上述目标语言语句集合中获取下一目标语言语句；也可以接收用户对上述第二按钮执行的触发操作，并根据上述触发操作和当前界面上显示的目标语言语句从上述目标语言语句集合中获取上一目标语言语句。
例如，在图3所示的翻译界面上显示有第一按钮即“查看下一条翻译结果”的按钮，用户在点击该按钮后可以看到更多的翻译结果。另外，如图4所示，翻译界面上也可以显示第二按钮即“查看上一条翻译结果”的按钮，用户点击此按钮可以返回查看上一条翻译结果。
另外，本发明实施例不仅可以应用在PC机上，也可以应用到手机等小屏幕终端上，其中，手机上显示的翻译界面可以如图5所示。需要说明的是，图5仅为一个示例，通常手机上显示的翻译界面除了“查看下一条翻译结果”的按钮外，还可以具有“查看上一条翻译结果”的按钮。
上述翻译信息的提供系统实施例，通过显示模块在当前界面显示获得的当前目标语言语句和预设控件，并通过切换显示模块根据用户对预设控件执行的操作获取另一目标语言语句，然后在上述当前界面显示上述另一目标语言语句，实现了通过快速、便捷的方式来提供一个完整句子的多种翻译结果，而无需像多候选项一样一个个重新选择单词或词组，从而让用户可以查看更多的翻译结果，有效地提高翻译的准确率，提升用户的满意度，另外，该实施例可以应用于手机等小屏幕终端，实用性强。
为了实现上述实施例，本发明还提出了一种存储介质，用于存储应用程序，该应用程序用于执行本发明任一个实施例所述的翻译信息的提供方法。
为了实现上述实施例，本发明还提出了一种翻译信息的提供设备，包括：一个或者多个处理器；存储器；一个或者多个模块，一个或者多个模块存储在存储器中，当被一个或者多个处理器执行时进行如下操作：
S1'、接收用户输入的源语言语句，并根据源语言语句获取当前目标语言语句。
S2'、在当前界面显示当前目标语言语句和预设控件。
S3'、接收用户对预设控件执行的操作，根据上述操作获取另一目标语言语句，并在 当前界面显示另一目标语言语句。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本发明的描述中，“多个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本发明的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本发明的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
应当理解，本发明的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如，如果用硬件来实现，和在另一实施方式中一样，可用本领域公知的下列技术 中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本发明各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器，磁盘或光盘等。尽管上面已经示出和描述了本发明的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本发明的限制，本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (12)

  1. 一种翻译信息的提供方法，其特征在于，包括：
    S1、接收用户输入的源语言语句，并根据所述源语言语句获取当前目标语言语句；
    S2、在当前界面显示所述当前目标语言语句和预设控件；以及
    S3、接收用户对所述预设控件执行的操作，根据所述操作获取另一目标语言语句，并在所述当前界面显示所述另一目标语言语句。
  2. 根据权利要求1所述的方法，其特征在于，还包括：
    获取与所述当前目标语言语句相关的目标语言语句集合，其中，所述目标语言语句集合中保存有按照置信度由高到低进行排序的目标语言语句。
  3. 根据权利要求1或2所述的方法，其特征在于，所述预设控件包括第一按钮和第二按钮。
  4. 根据权利要求3所述的方法，其特征在于，所述接收用户对所述预设控件执行的操作，根据所述操作获取另一目标语言语句，包括：
    接收用户对所述第一按钮执行的触发操作，并根据所述触发操作和当前界面上显示的目标语言语句从所述目标语言语句集合中获取下一目标语言语句；或者
    接收用户对所述第二按钮执行的触发操作，并根据所述触发操作和当前界面上显示的目标语言语句从所述目标语言语句集合中获取上一目标语言语句。
  5. 根据权利要求2所述的方法，其特征在于，所述获取与所述当前目标语言语句相关的目标语言语句集合，包括：
    获取所述当前目标语言语句的短语片段，并获取每个短语片段的候选片段，以构成候选片段集合；
    计算所述候选片段集合中每个候选片段的置信度，并按照置信度由高到低的顺序对所有候选片段进行排序；以及
    每次从当前候选片段集合中选取首个候选片段替换对应的短语片段，以生成所述目标语言语句集合中的一个目标语言语句，并按照生成的先后顺序保存对应的目标语言语句和从当前候选片段集合中删除被选取的候选片段，直至当前候选片段集合为空。
  6. 一种翻译信息的提供系统，其特征在于，包括：
    第一获取模块，用于接收用户输入的源语言语句，并根据所述源语言语句获取当前目标语言语句；
    显示模块，用于在当前界面显示所述当前目标语言语句和预设控件；以及
    切换显示模块，用于接收用户对所述预设控件执行的操作，根据所述操作获取另一目标 语言语句，并在所述当前界面显示所述另一目标语言语句。
  7. 根据权利要求6所述的系统，其特征在于，还包括：
    第二获取模块，用于：获取与所述当前目标语言语句相关的目标语言语句集合，其中，所述目标语言语句集合中保存有按照置信度由高到低进行排序的目标语言语句。
  8. 根据权利要求6或7所述的系统，其特征在于，所述预设控件包括第一按钮和第二按钮。
  9. 根据权利要求8所述的系统，其特征在于，所述切换显示模块，具体用于：
    接收用户对所述第一按钮执行的触发操作，并根据所述触发操作和当前界面上显示的目标语言语句从所述目标语言语句集合中获取下一目标语言语句；或者
    接收用户对所述第二按钮执行的触发操作，并根据所述触发操作和当前界面上显示的目标语言语句从所述目标语言语句集合中获取上一目标语言语句。
  10. 根据权利要求7所述的系统，其特征在于，所述第二获取模块包括：
    片段获取单元，用于获取所述当前目标语言语句的短语片段，并获取每个短语片段的候选片段，以构成候选片段集合；
    计算排序单元，用于计算所述候选片段集合中每个候选片段的置信度，并按照置信度由高到低的顺序对所有候选片段进行排序；以及
    语句获取单元，用于每次从当前候选片段集合中选取首个候选片段替换对应的短语片段，以生成所述目标语言语句集合中的一个目标语言语句，并按照生成的先后顺序保存对应的目标语言语句和从当前候选片段集合中删除被选取的候选片段，直至当前候选片段集合为空。
  11. 一种存储介质，其特征在于，用于存储应用程序，所述应用程序用于执行权利要求1至5中任一项所述的翻译信息的提供方法。
  12. 一种翻译信息的提供设备，其特征在于，包括：
    一个或者多个处理器；
    存储器；
    一个或者多个模块，所述一个或者多个模块存储在所述存储器中，当被所述一个或者多个处理器执行时进行如下操作：
    S1、接收用户输入的源语言语句，并根据所述源语言语句获取当前目标语言语句；
    S2、在当前界面显示所述当前目标语言语句和预设控件；以及
    S3、接收用户对所述预设控件执行的操作，根据所述操作获取另一目标语言语句，并在所述当前界面显示所述另一目标语言语句。
PCT/CN2015/083902 2015-03-27 2015-07-13 翻译信息的提供方法及系统 WO2016155144A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020167031835A KR101863484B1 (ko) 2015-03-27 2015-07-13 번역 정보 제공 방법 및 시스템
EP15887111.1A EP3142018A4 (en) 2015-03-27 2015-07-13 Method and system for providing translation information
JP2017535674A JP6517352B2 (ja) 2015-03-27 2015-07-13 翻訳情報の提供方法及びシステム
US15/322,515 US10176169B2 (en) 2015-03-27 2015-07-13 Method and system for providing translation information

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510142606.3A CN104731776B (zh) 2015-03-27 2015-03-27 翻译信息的提供方法及系统
CN201510142606.3 2015-03-27

Publications (1)

Publication Number Publication Date
WO2016155144A1 true WO2016155144A1 (zh) 2016-10-06

Family

ID=53455674

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/083902 WO2016155144A1 (zh) 2015-03-27 2015-07-13 翻译信息的提供方法及系统

Country Status (6)

Country Link
US (1) US10176169B2 (zh)
EP (1) EP3142018A4 (zh)
JP (1) JP6517352B2 (zh)
KR (1) KR101863484B1 (zh)
CN (1) CN104731776B (zh)
WO (1) WO2016155144A1 (zh)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104731776B (zh) * 2015-03-27 2017-12-26 百度在线网络技术（北京）有限公司 翻译信息的提供方法及系统
CN105808527A (zh) * 2016-02-24 2016-07-27 北京百度网讯科技有限公司 基于人工智能的定向翻译方法及装置
KR101884304B1 (ko) 2017-03-15 2018-08-02 주식회사 트위그팜 사용자별 번역 사전 생성, 관리, 및 활용을 위한 전자 문서 관리 시스템 및 전자 문서 관리 방법
JP6911785B2 (ja) * 2018-02-02 2021-07-28 日本電信電話株式会社 判定装置、判定方法及び判定プログラム
CN110209774A (zh) * 2018-02-11 2019-09-06 北京三星通信技术研究有限公司 处理会话信息的方法、装置及终端设备
CN110929504B (zh) * 2018-09-20 2023-05-30 阿里巴巴集团控股有限公司 语句诊断方法、装置和系统
CN110597882A (zh) * 2019-09-19 2019-12-20 北京明略软件系统有限公司 数据处理方法及装置、存储介质、电子装置
CN111399954A (zh) * 2020-03-10 2020-07-10 北京字节跳动网络技术有限公司 界面交互方法、装置、存储介质及电子设备
CN111753558B (zh) * 2020-06-23 2022-03-04 北京字节跳动网络技术有限公司 视频翻译方法和装置、存储介质和电子设备
CN111797215A (zh) * 2020-06-24 2020-10-20 北京小米松果电子有限公司 对话方法、装置及存储介质
KR20220004341A (ko) 2020-07-03 2022-01-11 주식회사 트위그팜 이메일 번역 서비스 제공 시스템 및 방법
KR102260396B1 (ko) 2020-09-09 2021-06-03 주식회사 트위그팜 범용 신경망 기계번역기를 활용한 하이브리드 번역 시스템
CN113111249A (zh) * 2021-03-16 2021-07-13 百度在线网络技术（北京）有限公司 搜索处理方法、装置、电子设备和存储介质
CN113111248A (zh) * 2021-03-16 2021-07-13 百度在线网络技术（北京）有限公司 搜索处理方法、装置、电子设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1426561A (zh) * 2000-04-24 2003-06-25 微软公司 带有跨语言阅读向导的计算机辅助阅读系统和方法
CN101320366A (zh) * 2007-06-07 2008-12-10 株式会社东芝 用于机器翻译的装置和方法
CN101763403A (zh) * 2009-12-31 2010-06-30 哈尔滨工业大学 面向多语言信息检索系统的查询翻译方法
CN103577394A (zh) * 2012-07-31 2014-02-12 阿里巴巴集团控股有限公司 一种基于双数组搜索树的机器翻译方法和装置
CN104731776A (zh) * 2015-03-27 2015-06-24 百度在线网络技术（北京）有限公司 翻译信息的提供方法及系统

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63136266A (ja) * 1986-11-28 1988-06-08 Sharp Corp 機械翻訳装置
JP3382974B2 (ja) * 1992-08-27 2003-03-04 株式会社東芝 データ解析装置および方法
JP2904059B2 (ja) * 1995-06-22 1999-06-14 富士ゼロックス株式会社 言語情報処理装置
US7107204B1 (en) * 2000-04-24 2006-09-12 Microsoft Corporation Computer-aided writing system and method with cross-language writing wizard
JP4410486B2 (ja) 2003-05-12 2010-02-03 インターナショナル・ビジネス・マシーンズ・コーポレーション 機械翻訳装置及びプログラム
US7346487B2 (en) * 2003-07-23 2008-03-18 Microsoft Corporation Method and apparatus for identifying translations
JP2005141490A (ja) * 2003-11-06 2005-06-02 Nippon Telegr & Teleph Corp <Ntt> 用例翻訳装置、用例翻訳処理方法、そのプログラム及び記録媒体
GB2415518A (en) * 2004-06-24 2005-12-28 Sharp Kk Method and apparatus for translation based on a repository of existing translations
US7822596B2 (en) * 2005-12-05 2010-10-26 Microsoft Corporation Flexible display translation
JP5011751B2 (ja) * 2006-02-27 2012-08-29 富士通株式会社 訳語情報出力処理プログラム，処理方法および処理装置
JP4113235B2 (ja) * 2006-12-22 2008-07-09 富士通株式会社 翻訳支援装置
CN101266600A (zh) * 2008-05-07 2008-09-17 陈光火 多媒体多语言互动同步翻译方法
US9081765B2 (en) 2008-08-12 2015-07-14 Abbyy Infopoisk Llc Displaying examples from texts in dictionaries
EP2261818A1 (en) * 2009-06-09 2010-12-15 Dudu Communications FZ-LLC A method for inter-lingual electronic communication
CN101937431A (zh) * 2010-08-18 2011-01-05 华南理工大学 情感语音翻译装置及处理方法
US8635059B2 (en) * 2010-11-15 2014-01-21 Google Inc. Providing alternative translations
CN102467498A (zh) * 2010-11-18 2012-05-23 阿里巴巴集团控股有限公司 翻译方法及装置
US8645364B2 (en) 2010-12-13 2014-02-04 Google Inc. Providing definitions that are sensitive to the context of a text
US9323746B2 (en) * 2011-12-06 2016-04-26 At&T Intellectual Property I, L.P. System and method for collaborative language translation
US9047274B2 (en) * 2013-01-21 2015-06-02 Xerox Corporation Machine translation-driven authoring system and method
US9183198B2 (en) * 2013-03-19 2015-11-10 International Business Machines Corporation Customizable and low-latency interactive computer-aided translation
EP3080715A2 (en) * 2013-12-09 2016-10-19 Google, Inc. Systems and methods for providing context based definitions and translations of text
KR101864361B1 (ko) * 2014-04-08 2018-06-04 네이버 주식회사 다양한 의미 범주에 기반한 번역 결과 제공 방법 및 시스템

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1426561A (zh) * 2000-04-24 2003-06-25 微软公司 带有跨语言阅读向导的计算机辅助阅读系统和方法
CN101320366A (zh) * 2007-06-07 2008-12-10 株式会社东芝 用于机器翻译的装置和方法
CN101763403A (zh) * 2009-12-31 2010-06-30 哈尔滨工业大学 面向多语言信息检索系统的查询翻译方法
CN103577394A (zh) * 2012-07-31 2014-02-12 阿里巴巴集团控股有限公司 一种基于双数组搜索树的机器翻译方法和装置
CN104731776A (zh) * 2015-03-27 2015-06-24 百度在线网络技术（北京）有限公司 翻译信息的提供方法及系统

Also Published As

Publication number Publication date
US20170139906A1 (en) 2017-05-18
KR20160145140A (ko) 2016-12-19
JP2018500698A (ja) 2018-01-11
KR101863484B1 (ko) 2018-05-31
CN104731776B (zh) 2017-12-26
CN104731776A (zh) 2015-06-24
JP6517352B2 (ja) 2019-05-22
US10176169B2 (en) 2019-01-08
EP3142018A1 (en) 2017-03-15
EP3142018A4 (en) 2018-03-14

Similar Documents

Publication Publication Date Title
WO2016155144A1 (zh) 翻译信息的提供方法及系统
US11288444B2 (en) Optimization techniques for artificial intelligence
US9043300B2 (en) Input method editor integration
CN107608532B (zh) 一种联想输入方法、装置及电子设备
JP7412382B2 (ja) イベント抽出方法、イベント抽出装置、電子デバイス、記憶媒体及びコンピュータプログラム製品
CN107305438B (zh) 候选项的排序方法和装置、用于候选项排序的装置
JP2012533818A (ja) 単語の重みに基づいた検索結果の順位付け
US20140040741A1 (en) Smart Auto-Completion
CN107526846B (zh) 频道排序模型的生成、排序方法、装置、服务器和介质
WO2019169858A1 (zh) 一种基于搜索引擎技术的数据分析方法及系统
CN106776583A (zh) 机器翻译评价方法和设备及机器翻译方法和设备
WO2016150346A1 (zh) 文本输入方法和装置
WO2020024455A1 (zh) 基于上下文的输入方法、装置、存储介质及计算机设备
EP3308293A1 (en) Methods and computing devices relating to translation of a single word speech input
CN109582155B (zh) 输入联想词的推荐方法、装置、存储介质及电子设备
US9910918B2 (en) Presenting tags of a tag cloud in a more understandable and visually appealing manner
EP3255566A1 (en) Text retrieval method and apparatus
CN111666417B (zh) 生成同义词的方法、装置、电子设备以及可读存储介质
CN112559711A (zh) 一种同义文本提示方法、装置及电子设备
TWI492072B (zh) 輸入系統及其方法
CN109308151B (zh) 一种信息处理方法、装置、设备及存储介质
US20150006524A1 (en) Auto-search textbox in a content submission system
KR101593145B1 (ko) 연관 질의어 제공 시스템 및 방법
JP2021096761A (ja) 検索支援装置
CN117119046A (zh) 服务的调用方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 20167031835

Country of ref document: KR

Kind code of ref document: A

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

Ref document number: 15887111

Country of ref document: EP

Kind code of ref document: A1

REEP Request for entry into the european phase

Ref document number: 2015887111

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2015887111

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 15322515

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2017535674

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE