WO2021259061A1 - 文档翻译方法和装置、存储介质和电子设备 - Google Patents

文档翻译方法和装置、存储介质和电子设备 Download PDF

Info

Publication number
WO2021259061A1
WO2021259061A1 PCT/CN2021/099109 CN2021099109W WO2021259061A1 WO 2021259061 A1 WO2021259061 A1 WO 2021259061A1 CN 2021099109 W CN2021099109 W CN 2021099109W WO 2021259061 A1 WO2021259061 A1 WO 2021259061A1
Authority
WO
WIPO (PCT)
Prior art keywords
translation
user
suggestion
area
input
Prior art date
Application number
PCT/CN2021/099109
Other languages
English (en)
French (fr)
Inventor
杜育璋
朱培豪
周崇兴
陈一鸣
王明轩
李磊
Original Assignee
北京字节跳动网络技术有限公司
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 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Priority to JP2022545064A priority Critical patent/JP2023511971A/ja
Priority to KR1020227029309A priority patent/KR20220123736A/ko
Priority to EP21828949.4A priority patent/EP4083849A4/en
Publication of WO2021259061A1 publication Critical patent/WO2021259061A1/zh
Priority to US17/872,966 priority patent/US11580314B2/en

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
    • G06F40/47—Machine-assisted translation, e.g. using translation memory
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/103—Formatting, i.e. changing of presentation of documents
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • 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

  • the present disclosure relates to the field of machine translation, and in particular, to a document translation method and device, storage medium, and electronic equipment.
  • the content of the invention is provided to introduce concepts in a brief form, and these concepts will be described in detail in the following specific embodiments.
  • the content of the invention is not intended to identify the key features or essential features of the technical solution that is required to be protected, nor is it intended to be used to limit the scope of the technical solution that is required to be protected.
  • the present disclosure provides a document translation method, including:
  • the translation suggestion is displayed in the editing area as the translation result
  • a document translation device including:
  • a display module for displaying an original text display area, a translation area, and an editing area, wherein the original text display area displays the text content in the document to be translated, and the translation area displays a reference translation of the text content;
  • the suggestion module is used to follow the user's input in the editing area and provide translation suggestions from the reference translation;
  • the suggestion module is further configured to display the translation suggestion in the editing area as a translation result in the case of detecting a user's confirmation operation for the translation suggestion, or, when it is detected that the user has a suggestion for the translation In the case of a non-confirmation operation, receiving a translation input by the user that is different from the translation suggestion, and displaying the translation input by the user as the translation result in the editing area.
  • the present disclosure provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing device, the steps of the method described in the first aspect of the present disclosure are implemented.
  • an electronic device including:
  • a storage device on which a computer program is stored
  • the processing device is configured to execute the computer program in the storage device to implement the steps of the method in the first aspect of the present disclosure.
  • translation suggestions from reference translations can be provided based on user input, and users can directly use translation suggestions as translation results through confirmation operations, reducing user input time.
  • This disclosure combines Manual accuracy and machine efficiency can improve the efficiency and quality of translation.
  • Fig. 1 is a flow chart showing a method for document translation according to an exemplary disclosed embodiment.
  • Fig. 2 is a schematic diagram showing a translation interface according to an exemplary disclosed embodiment.
  • Fig. 3 is a schematic diagram showing a translation interface according to an exemplary disclosed embodiment.
  • Fig. 4 is a block diagram showing a document translation device according to an exemplary disclosed embodiment.
  • Fig. 5 is a block diagram showing an electronic device according to an exemplary disclosed embodiment.
  • Fig. 1 is a flowchart of a document translation method according to an exemplary disclosed embodiment.
  • the method can be applied to terminals, servers and other independent electronic devices, and can also be applied to a translation system.
  • the method in the method Each step can be completed by multiple devices in the translation system.
  • S11 shown in FIG. 1 can be executed by a terminal, and S12 can be executed by a server.
  • the document translation method includes the following steps:
  • the original text display area displays the text content in the document to be translated, and the reference translation of the text content is displayed in the translation area.
  • the method provided by the embodiment of the present disclosure includes displaying the translation suggestion as the translation result in the editing area in the case of detecting the user's confirmation operation for the translation suggestion, and when it is detected that the user is targeting the translation suggestion In the case of a non-confirmation operation of the translation suggestion, a translation that is different from the translation suggestion input by the user is received, and the translation input by the user is displayed in the editing area as the translation result.
  • the method can also update the reference translation in the translation area according to the translation input by the user.
  • the above confirmation operation may be a user's operation on a preset shortcut key.
  • the user indicates the intention of adopting the translation suggestion by clicking the shortcut key. Therefore, the translation suggestion can be displayed in the editing area as the translation result when the user's clicking the shortcut key is detected.
  • step S12 is It shows that the method provided by the embodiment of the present disclosure can respond to the translation suggestion provided this time as the translation result displayed in the editing area, and then provide the next translation suggestion from the reference translation (the next translation suggestion may be the provided translation result) The translation is suggested in the follow-up translation in the reference translation).
  • the foregoing detection of the non-confirmation operation of the user for the translation suggestion may be the detection of the inconsistency between the translation input by the user and the translation suggestion provided this time.
  • the method provided by the embodiments of the present disclosure can receive a translation input by the user that is different from the suggested translation, and display the translation input by the user as the translation result in the editing area. Further, the method can also be based on the user input The translation updates the reference translation in the translation area.
  • step S12 indicates that this The method provided by the disclosed embodiment can provide the next translation suggestion from the reference translation updated according to the translation input by the user in response to the user inputting a translation in the editing area that is different from the translation suggestion.
  • the translation suggestion provided this time is "my”. If it is detected that the translation input by the user is a translation "I” that is different from the translation suggestion "my”, the reference translation is updated according to the translation "I”, and the updated Suggestions for the next translation of the translation "I" are provided in the reference translation of.
  • the translation suggestions from the reference translation can be provided according to the user's input, and the user can directly use the translation suggestion as the translation result through the confirmation operation, reducing the user's input time.
  • the present disclosure combines manual accuracy and machine efficiency , Can improve the efficiency of translation and the quality of translation.
  • the document to be translated in step S11 may be text content directly copied and pasted by the user, or text document, image document, etc. uploaded by the user.
  • the present disclosure does not limit the format of the document to be translated.
  • text recognition can be performed on the picture document to obtain the text content in the picture document.
  • the providing translation suggestions in step S12 may include: highlighting the translation suggestions from the reference translation in the translation area.
  • the highlighting of the translation suggestion in the translation area can be cancelled.
  • the highlighting can be bold fonts, highlighted fonts, heterochromatic characters, heterochromatic backgrounds, shading effects, etc., which can highlight the translation suggestions.
  • the highlighting may be a display mode different from the display mode of the input translation.
  • the input translation may be a bold font, and the translation suggestion is a normal font, or ,
  • the input translation can be black words, and the translation suggestions are gray words, etc.
  • the display mode of the translation suggestion can be adjusted to be the same as the display method of the input translation.
  • the input translation may be in bold font, and the translation suggestion is in normal font.
  • the translation suggestion is adjusted to be displayed in bold font.
  • the confirmation operation may be an input operation of a shortcut key of the electronic device by the user.
  • the electronic device may be a mobile phone, and the shortcut key may be a virtual key on the display area of the mobile phone or a physical key of the mobile phone (for example, a volume key), and the user can operate the aforementioned shortcut key to adopt the translation suggestion.
  • the translation suggestion can be displayed in the editing area as the translation result.
  • the electronic device may also be a computer, and the shortcut key may be a designated or custom key on the computer keyboard or mouse (for example: keyboard alt key, mouse side key, etc.).
  • the confirmation operation may also be a gesture confirmation operation recognized after being acquired by the camera, such as nodding, blinking, making a preset gesture, etc., or may also be a voice confirmation operation recognized after being acquired by a microphone.
  • the translation suggestion from the reference translation includes at least one of a word, a phrase, and a sentence.
  • the user When the user translates the text content, he can refer to the reference translation displayed in the translation area and input in the editing area (it is worth noting that the input here includes the input of characters, such as typing letters, words, etc., as well as Key operation input, such as clicking the editing area, etc.), can provide translation suggestions from the reference translation.
  • the reference translation is "When the bell rang, Allie entered the school”
  • the user can adopt the translation suggestion through a confirmation operation, and use the confirmation operation as an input operation in the editing area to continue to provide translation suggestions from the reference translation. For example, in the case of detecting the user's confirmation operation for "When", "When” is displayed as the translation result in the editing area, and the user is provided with the next translation suggestion "the".
  • the non-confirmation operation can be a preset operation that represents non-confirmation (for example, clicking a preset button, making a preset action, etc.), or can refer to other situations than the aforementioned confirmation operation.
  • the confirmation operation is not performed within the preset time, or the input operation is continued.
  • the reference translation of the text content "When the bell rang, Allie entered the school” is "When the bell rang, Allie entered the school.”
  • the reference translation can be updated to "When the bell rang, Allie came in the school.” The user provides a translation suggestion "came”.
  • the reference translation and translation suggestions can be provided by machine translation (for example, a deep learning translation model, etc.). It is worth noting that when a reference translation that conforms to the text content cannot be generated based on the translation entered by the user in the editing area, the user can correct the translation characters entered by the user based on the pre-stored dictionary content, and update the translation based on the corrected translation.
  • the reference translation can be provided by machine translation (for example, a deep learning translation model, etc.).
  • the translation language is English and the original text is Chinese as examples in this disclosure, this disclosure does not limit the language of translation and the language of the original text.
  • the original text in this disclosure may also be Chinese classical Chinese or translated text. It can be in the Chinese vernacular, or in various combinations such as the original text in Japanese and the translated text in English.
  • the original text display area is an editable area, that is, the text content in the original text display area can be edited.
  • the method further includes updating the reference translation in the translation area in response to the user's operation of modifying the text content in the original text display area.
  • the reference translation of the text content "When the bell rang, Allie entered the school.” is referred to as "When the bell rang, Allie entered the school.”, after receiving the text content in the original display area from the user After "school” is changed to "classroom", the reference translation in the translation area can be updated to "When the bell rang, Allie entered the classroom.”
  • the text content in the document to be translated may be segmented to obtain multiple segmented content, and for each segmented content, the corresponding original text display area, translation area, and editor are displayed. area.
  • the original text display area displays the corresponding segmented content
  • the translation area displays the reference translation of the corresponding segmented content.
  • the text content can be manually segmented by the user. For example, insert a segmentation mark where you need to segment.
  • the text content can also be segmented according to the semantic information and/or segmentation character information of the text content in the document to be translated.
  • the semantic segmentation model can be used to segment according to the text content, and the same semantic sentence can be displayed as a natural segment.
  • Figure 2 shows a schematic diagram of a possible translation interface.
  • the text content of the document to be translated is displayed in the original text display area, which is displayed above the target text area and the editing area, and different paragraphs have different original text display areas, target text areas, and editing areas.
  • Each area of each paragraph can be translated independently and will not be updated due to the modification of other areas.
  • the user can enter the translation in the editing area, or modify the text content in the original display area.
  • the editing area may be displayed in response to the user's selection operation on the paragraph, and the editing area may be hidden before the user selects the paragraph.
  • Figure 3 shows a schematic diagram of a possible translation interface.
  • the original text display area can be located above the target text area and the editing area.
  • the text content can be translated, and the reference translation can be displayed in the translation area, and following the user's input in the editing area, the translation suggestions from the reference translation can be provided in the editing area.
  • the translation suggestions that have been confirmed as the translation results, or the translation that the user has entered are displayed in bold font, and the translation suggestions being displayed are displayed in gray normal font.
  • a non-confirmation operation of the user inputting a translation in the editing area is detected (such as inputting a translation that is different from the suggested translation in the editing area), according to the translation input by the user (the characters displayed in bold and underlined are The characters input by the user) update the reference translation, and show the user the translation suggestions from the updated reference translation.
  • the translation suggestion is displayed in the editing area as a translation result.
  • the user edits the text content of the original text display area (the text displayed in bold and underlined is the text modified by the user), then the reference translation is updated based on the text content edited by the user, and translation suggestions from the reference translation are provided.
  • the text content and the user's translation result of the text content can be used as training samples, and the training samples are used to train the user's corresponding deep learning translation model to learn the deep learning
  • the translation model is updated to make the deep learning translation model more in line with users' habits. For example, if the user is used to translating the word “phone” into “phone” instead of "telephone", after the user has used it multiple times, the user's corresponding deep learning translation model can be updated based on the user's translation results, so that in subsequent uses, Translate the word "telephone” into “phone” instead of "telephone” to make it more in line with the user's habits.
  • the translation result may be exported as a translation document in a document format specified by the user, and a download service may be provided to the user.
  • the method can also generate a translated document consistent with the typesetting format according to the typesetting format in the document to be translated uploaded by the user, thereby achieving the effect of saving the typesetting time of the user.
  • the margins in the document to be translated are 3 cm in the upper part, 2.5 cm in the lower part, 2.8 cm in the left part, and 2 cm in the right part, and the title size is HeiTi No. 2 in the middle, the subtitle is HeiTi No.
  • translation suggestions from reference translations can be provided based on user input, and users can directly use translation suggestions as translation results through confirmation operations, reducing user input time.
  • This disclosure combines Manual accuracy and machine efficiency can improve the efficiency and quality of translation.
  • Fig. 4 is a block diagram showing a document translation device according to an exemplary disclosed embodiment. As shown in Fig. 4, the document translation device 400 includes:
  • the display module 410 is configured to display an original text display area, a translation area, and an editing area, wherein the original text display area displays the text content in the document to be translated, and the translation area displays a reference translation of the text content.
  • the suggestion module 420 is configured to follow the user's input in the editing area and provide translation suggestions from the reference translation.
  • the suggestion module 420 is further configured to display the translation suggestion in the editing area as the translation result in the case of detecting the user's confirmation operation for the translation suggestion, or, when it is detected that the user is targeting the translation In the case of a suggested non-confirmation operation, a translation input by the user that is different from the suggested translation is received, and the translation input by the user is displayed in the editing area as the translation result.
  • the suggestion module is further configured to update the reference translation in the translation area according to the translation input by the user.
  • the suggestion module further includes a display sub-module, configured to highlight the translation suggestion from the reference translation in the translation area, and cancel if the user's confirmation operation for the translation suggestion is detected The translation suggestion is highlighted in the translation area.
  • the display submodule is configured to display the translation suggestion in a display mode different from the input translation in the editing area, and in the case of detecting a user's confirmation operation for the translation suggestion, The translation suggestion as the translation result is displayed in the editing area in the same manner as the display manner of the input translation.
  • the translation suggestion includes at least one of words, phrases, and sentences
  • the suggestion module is further configured to display the translation suggestion as a translation result in the editing area in response to a user's triggering operation of a shortcut key on the electronic device.
  • the device further includes a modification module for updating the reference translation in the translation area in response to a user's operation of modifying the text content in the original text display area.
  • the display module further includes a segmentation sub-module, which is used to segment the text content in the document to be translated to obtain a plurality of segmented content; the display module is also used for each segment
  • the segment content displays the corresponding original text display area, translation area, and editing area, wherein the original text display area displays the corresponding segment content, and the translation area displays the reference translation of the corresponding segment content.
  • the segmentation sub-module is configured to segment the text content according to semantic information and/or segmentation symbol information of the text content in the document to be translated to obtain multiple segmented contents.
  • translation suggestions from reference translations can be provided based on user input, and users can directly use translation suggestions as translation results through confirmation operations, reducing user input time.
  • This disclosure combines Manual accuracy and machine efficiency can improve the efficiency and quality of translation.
  • FIG. 5 shows a schematic structural diagram of an electronic device (for example, the terminal device or the server in FIG. 1) 500 suitable for implementing the embodiments of the present disclosure.
  • Terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (e.g. Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 5 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the electronic device 500 may include a processing device (such as a central processing unit, a graphics processor, etc.) 501, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 502 or from a storage device 508.
  • the program in the memory (RAM) 503 executes various appropriate actions and processing.
  • various programs and data required for the operation of the electronic device 500 are also stored.
  • the processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504.
  • An input/output (I/O) interface 505 is also connected to the bus 504.
  • the following devices can be connected to the I/O interface 505: including input devices 506 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCD), speakers, vibrations
  • input devices 506 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.
  • LCD liquid crystal displays
  • An output device 507 such as a device
  • a storage device 508 such as a magnetic tape, a hard disk, etc.
  • the communication device 509 may allow the electronic device 500 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 5 shows an electronic device 500 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may alternatively be implemented or provided with more or fewer devices.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502.
  • the processing device 501 the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
  • the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the client and server can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
  • Communication e.g., communication network
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future research and development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the electronic device displays an original text display area, a translation area, and an editing area, wherein the original text display area
  • the text content in the document to be translated is displayed in the document to be translated, and the reference translation of the text content is displayed in the translation area; following the user’s input in the editing area, translation suggestions from the reference translation are provided; wherein, in When the user's confirmation operation for the translation suggestion is detected, the translation suggestion is displayed in the editing area as the translation result, or when the user's non-confirmation operation for the translation suggestion is detected
  • receiving a translation input by the user that is different from the translation suggestion and displaying the translation input by the user as the translation result in the editing area.
  • the computer program code used to perform the operations of the present disclosure can be written in one or more programming languages or a combination thereof.
  • the above-mentioned programming languages include, but are not limited to, object-oriented programming languages—such as Java, Smalltalk, C++, and Including conventional procedural programming languages-such as "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to Connect via the Internet).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions can also occur in a different order from the order marked in the drawings. For example, two blocks shown one after the other can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the modules involved in the embodiments described in the present disclosure can be implemented in software or hardware.
  • the name of the module does not constitute a limitation on the module itself under certain circumstances.
  • the display module can also be described as "a module that displays the original text display area, the translation area, and the editing area".
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Product
  • SOC System on Chip
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium, which may contain or store a program for use by the instruction execution system, apparatus, or device or in combination with the instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • the machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing.
  • machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read only memory
  • magnetic storage device or any suitable combination of the foregoing.
  • Example 1 provides a document translation method, including displaying an original text display area, a target text area, and an editing area, wherein the original text display area displays the text content in the document to be translated, The reference translation of the text content is displayed in the translation area; following the user's input in the editing area, a translation suggestion from the reference translation is provided; wherein, when the user's confirmation of the translation suggestion is detected In the case of operation, display the translation suggestion as a translation result in the editing area; in the case of detecting a user's non-confirmation operation for the translation suggestion, receiving a translation input by the user that is different from the translation suggestion, The translation input by the user is displayed in the editing area as the translation result.
  • Example 2 provides the method of Example 1, and the method further includes: updating the reference translation in the translation area according to the translation input by the user.
  • Example 3 provides the method of Example 1.
  • the providing translation suggestions from the reference translation includes: highlighting the translation suggestions from the reference translation in the translation area;
  • the method further includes: canceling the highlight display of the translation suggestion in the translation area in the case of detecting the user's confirmation operation for the translation suggestion.
  • Example 4 provides the method of Example 3.
  • the providing the translation suggestion from the reference translation includes: displaying the translation in the editing area in a display manner different from the input translation.
  • the translation suggestion; and in the case of detecting the user's confirmation operation for the translation suggestion, displaying the translation suggestion as the translation result in the editing area includes: after detecting that the user has the translation suggestion
  • the translation suggestion as the translation result is displayed in the editing area in the same manner as the display manner of the input translation.
  • Example 5 provides the method of Example 1, and the translation suggestion includes at least one of a word, a phrase, and a sentence.
  • Example 6 provides the method of Example 1.
  • the translation suggestion is displayed to the translation result as a translation result.
  • the editing area includes: in response to a user's triggering operation on the shortcut key on the electronic device, displaying the translation suggestion as a translation result to the editing area.
  • Example 7 provides the method of Examples 1-6, and the method further includes: in response to a user's operation of modifying the text content in the original text display area, updating the translation Reference translation in the area.
  • Example 8 provides the method of Examples 1-6.
  • the displaying the original text display area, the target text area, and the editing area includes: segmenting the text content in the document to be translated, Obtain multiple segmented content; for each segmented content, display the corresponding original text display area, translation area, and editing area, wherein the original text display area displays the corresponding segmented content, and the translation area displays The reference translation of the corresponding segmented content.
  • Example 9 provides the method of Example 8.
  • the segmenting the text content in the document to be translated to obtain multiple segmented content includes: according to the document to be translated Semantic information and/or segmentation character information of the text content within, segment the text content to obtain multiple segmented contents.
  • Example 10 provides a document translation device including a display module for displaying an original text display area, a target text area, and an editing area, wherein the original text display area displays a document to be translated
  • the reference translation of the text content is displayed in the translation area
  • the suggestion module is used to follow the user’s input in the editing area and provide translation suggestions from the reference translation
  • the suggestion The module 420 is further configured to display the translation suggestion as a translation result in the editing area in the case of detecting the user's confirmation operation for the translation suggestion, and when the user's non-confirmation of the translation suggestion is detected
  • receiving a translation input by the user that is different from the translation suggestion and displaying the translation input by the user as the translation result in the editing area.
  • Example 11 provides the apparatus of Example 10, and the suggestion module is further configured to update the reference translation in the translation area according to the translation input by the user.
  • Example 12 provides the device of Example 10.
  • the suggestion module further includes a display sub-module for highlighting translation suggestions from the reference translation in the translation area, and In the case of detecting the user's confirmation operation for the translation suggestion, cancel the highlight display of the translation suggestion in the translation area.
  • Example 13 provides the device of Example 12.
  • the display submodule is configured to display the translation suggestion in a display mode different from the input translation in the editing area;
  • the translation suggestion as the translation result is displayed in the editing area in the same manner as the display manner of the input translation.
  • Example 14 provides the apparatus of Example 10, and the translation suggestion includes at least one of a word, a phrase, and a sentence.
  • Example 15 provides the apparatus of Example 10.
  • the suggestion module is further configured to respond to the user's triggering operation of the shortcut key on the electronic device, and use the translation suggestion as the translation result Display to the editing area.
  • Example 16 provides the device of Examples 10-15, and the device further includes a modification module for responding to a user's operation of modifying the text content in the original text display area, Update the reference translation in the translation area.
  • Example 17 provides the devices of Examples 10-15, and the display module further includes a segmentation sub-module for segmenting the text content in the document to be translated to obtain multiple Segmented content; the display module is also used to display the corresponding original text display area, translation area, and editing area for each segmented content, wherein the original text display area displays the corresponding segmented content, so The translation area displays the reference translation of the corresponding segmented content.
  • a segmentation sub-module for segmenting the text content in the document to be translated to obtain multiple Segmented content
  • the display module is also used to display the corresponding original text display area, translation area, and editing area for each segmented content, wherein the original text display area displays the corresponding segmented content, so The translation area displays the reference translation of the corresponding segmented content.
  • Example 18 provides the apparatus of Example 117, and the segmentation submodule is configured to perform a correction based on the semantic information and/or segmentation information of the text content in the document to be translated The text content is segmented to obtain multiple segmented contents.

Landscapes

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

Abstract

一种文档翻译方法和装置、存储介质和电子设备，所述方法包括：展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文（S11）；跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议（S12）；其中，在检测到用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域；在检测到用户针对所述译文建议的非确认操作的情况下，接收用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。该方法可以提升翻译的效率以及翻译的质量。

Description

文档翻译方法和装置、存储介质和电子设备
本申请要求于2020年06月23日提交国家知识产权局、申请号为202010584747.1、申请名称为“文档翻译方法和装置、存储介质和电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及机器翻译领域，具体地，涉及一种文档翻译方法和装置、存储介质和电子设备。
背景技术
在机器翻译发达的如今，简单的翻译任务已经可以通过机器翻译加人工校对的方式进行，也就是采用MTPE(Machine Translation Post-Editting，机器译后编辑)的模式进行。但现在的MTPE技术下，机器翻译和人工校对不能很好地兼容，导致文档翻译的质量仍旧不及人工翻译，这些问题严重制约了MTPE的发展。在对翻译结果的准确性要求较高的翻译场景下，通常还是会使用人工翻译的方式进行文档翻译，人工翻译效率较低、速度较慢的问题仍旧无法解决。
发明内容
提供该发明内容部分以便以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。该发明内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
第一方面，本公开提供一种文档翻译方法，包括：
展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文；
跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议；
其中，在检测到用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域；或者，
在检测到用户针对所述译文建议的非确认操作的情况下，接收用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。
第二方面，本公开提供一种文档翻译装置，包括：
展示模块，用于展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文；
建议模块，用于跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议；
所述建议模块，还用于在检测到用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域，或者，在检测到用户针对所述译文建议的非 确认操作的情况下，接收用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。
第三方面，本公开提供一种计算机可读介质，其上存储有计算机程序，该程序被处理装置执行时实现本公开第一方面中所述方法的步骤。
第四方面，本公开提供一种电子设备，包括：
存储装置，其上存储有计算机程序；
处理装置，用于执行所述存储装置中的所述计算机程序，以实现本公开第一方面中所述方法的步骤。
基于上述的技术方案，至少可以达到以下技术效果：可以根据用户的输入提供来自参考译文的译文建议，并且，用户可以通过确认操作直接将译文建议作为译文结果，减少用户的输入时间，本公开结合人工的准确性及机器的高效性，可以提升翻译的效率以及翻译的质量。
本公开的其他特征和优点将在随后的具体实施方式部分予以详细说明。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。在附图中：
图1是根据一示例性公开实施例示出的一种文档翻译方法的流程图。
图2是根据一示例性公开实施例示出的一种翻译界面的示意图。
图3是根据一示例性公开实施例示出的一种翻译界面的示意图。
图4是根据一示例性公开实施例示出的一种文档翻译装置的框图。
图5是根据一示例性公开实施例示出的一种电子设备的框图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单 元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
图1是根据一示例性公开实施例示出的一种文档翻译方法的流程图，本方法可以应用于终端、服务器及其他独立电子设备，也可以应用于翻译系统，此种情况下，方法中的各个步骤可以由翻译系统中的多个设备配合完成，例如图1中所示的S11可以由终端执行，S12可以由服务器执行等。如图1所示，该文档翻译方法包括以下步骤：
S11、展示原文显示区域、译文区域以及编辑区域，该原文显示区域中显示有待翻译文档中的文本内容，该译文区域中显示有对该文本内容的参考译文。
S12、跟随用户在该编辑区域内的输入，提供来自该参考译文的译文建议。
其中，基于该译文建议，本公开实施例提供的方法包括在检测到用户针对该译文建议的确认操作的情况下，将该译文建议作为译文结果显示到该编辑区域，以及在检测到用户针对该译文建议的非确认操作的情况下，接收用户输入的不同于该译文建议的译文，将用户输入的译文作为译文结果显示到编辑区域。可选的，该方法还可以根据用户输入的译文更新该译文区域中的参考译文。
在具体实施时，上述确认操作可以是用户针对预设的快捷键的操作。例如，用户通过点击该快捷键表明采纳译文建议的意图，因此，可以在检测到用户点击快捷键的操作的情况下，将该译文建议作为译文结果显示到该编辑区域。值得说明的是，将译文建议作为译文结果显示到该编辑区域这一动作将作为步骤S12中所述的用户在该编辑区域内的输入，也就是说，在此种情况下，步骤S12即是表明，本公开实施例提供的方法可以响应于将本次提供的译文建议作为译文结果显示到该编辑区域，接着提供来自该参考译文的下一个译文建议(该下一个译文建议可以是已提供的译文建议在参考译文中的后续译文)。
可选地，上述检测到用户针对该译文建议的非确认操作的情况可以是检测到用户输入的译文与本次提供的译文建议不一致的情况。在此种情况下，本公开实施例提供的方法可以接收用户输入的不同于该译文建议的译文，将用户输入的译文作为译文结果显示到编辑区域，进一步的，该方法还可以根据用户输入的译文更新该译文区域中的参考译文。同样值得说明的是，用户输入的与译文建议不同的译文，将作为步骤S12中所述的用户在该编辑区域内的输入，也就是说，在此种情况下，步骤S12即是表明，本公开实施例提供的方法可以响应于用户在该编辑区域输入与译文建议不同的译文，提供来自根据用户输入的译文更新后的参考译文的下一个译文建议。例如，本次提供的译文建议为“my”，在检测到用户输入的译文为不同与译文建议“my”的译文“I”的情况下，根据译文“I”更新参考译文，并从更新后的参考译文中提供译文“I”的下一个译文建议。
采用上述方法，可以根据用户的输入提供来自参考译文的译文建议，并且，用户可以通过确认操作直接将译文建议作为译文结果，减少用户的输入时间，本公开结合人工的准确性及机器的高效性，可以提升翻译的效率以及翻译的质量。
为了使本领域技术人员更加理解本公开实施例提供的技术方案，下面对本公开实施例提供的文档翻译方法进行详细说明。
可选地，步骤S11中的待翻译文档可以是用户直接复制粘贴的文字内容，也可以是用户上传的文本文档、图片文档等，本公开不对待翻译文档的格式进行限制。针对图片文档等格式的文档时，可以对所述图片文档进行文字识别，以获取图片文档中的文本内容。
可选地，步骤S12中的所述提供译文建议可以包括：在所述译文区域突出显示来自所述参考译文的所述译文建议。在此种情况下，在检测到用户针对该译文建议的确认操作的情况下，可以取消所述译文建议在所述译文区域的突出显示。
该突出显示可以是加粗字体、高亮字体、异色字、异色背景、底纹效果等可以将译文建议突出展示的显示方式。在一种可能的实施方式中，该突出显示可以是与已输入译文的显示方式不同的显示方式，例如，在编辑区域中，已输入的译文可以是加粗字体，译文建议是正常字体，或者，已输入的译文可以是黑色字，译文建议是灰色字等。在检测到用户针对译文建议的确认操作的情况下，可以将译文建议的显示方式调整为与已输入译文的显示方式相同。例如，已输入的译文可以是加粗字体，译文建议是正常字体，在检测到用户的确认操作的情况下，将该译文建议调整为加粗字体显示。
在一种可能的实施方式中，该确认操作可以是用户对电子设备的快捷键的输入操作。例如，该电子设备可以是手机，该快捷键可以是手机显示区域上的虚拟键或手机的实体键(例如：音量键)，用户可以对上述的快捷键进行操作以采纳该译文建议。在检测到用户对上述快捷键的触发操作的情况下，可以将译文建议作为译文结果显示到编辑区域。其中，该电子设备还可以是电脑，该快捷键可以是电脑键盘或鼠标上的指定或自定义按键(例如：键盘alt键、鼠标侧键等)。
该确认操作还可以是由摄像头获取后识别得到的姿势确认操作，如点头、眨眼、作出预设手势等，还可以是由麦克风获取后识别得到的语音确认操作。
在一种可能的实施方式中，该来自所述参考译文的译文建议包括词、词组、句子中的至少一项。
下面对译文建议的提供方式进行详细阐述：
在用户针对文本内容进行翻译时，可以参考在译文区域中显示的参考译文，在编辑区域内进行输入(值得说明的是，此处的输入包括字符的输入，例如键入字母、单词等，也包括按键操作输入，例如点击编辑区域等)，可以提供来自参考译文的译文建议。
例如，文本内容为“当铃声响起时，艾莉走进了学校”，参考译文为“When the bell rang,Allie entered the school”，则在用户点击编辑区域，或者在编辑区域输入了字符“W”之后，可以提供来自参考译文的译文建议“When”(或者“When the bell rang”等更粗粒度的译文建议)。
用户可以通过确认操作采纳该译文建议，并且，将该确认操作作为在编辑区域内的输入操作，继续提供来自参考译文的译文建议。例如，在检测到用户针对“When”的确认操作的情况下，将“When”作为译文结果显示到编辑区域，并为用户提供下一译文建议“the”。
在检测到用户针对译文建议的非确认操作的情况下，接收用户输入的不同于译文建议 的译文，并根据用户输入的译文更新译文区域中的参考译文。其中，该非确认操作可以是预设的代表非确认的操作(例如点击预设按键、做出预设动作等)，也可以是指除了前述的确认操作以外的其他情况。例如，在预设时间内没有进行确认操作，或者进行了继续输入的操作。
在一些实施例中，文本内容“当铃声响起时，艾莉走进了学校”的参考译文为“When the bell rang,Allie entered the school.”，在接收到用户对编辑区域的点击输入操作后，提供来自参考译文的译文建议“When”，并基于用户的确认操作，将译文建议“When”作为译文结果显示到编辑区域，并继续为用户提供下一译文建议“the”。在提供译文建议“entered”时，接收到了用户不同于译文建议的输入“c”，则可以基于用户输入的译文，更新参考译文为“When the bell rang,Allie came in the school.”，并为用户提供译文建议“came”。
其中，参考译文以及译文建议可以由机器翻译(例如深度学习翻译模型等)提供。值得说明的是，当基于所述用户在编辑区域输入的译文无法生成符合文本内容的参考译文时，可以基于预存的词典内容对用户输入的译文字符进行纠错，并根据纠错后的译文更新该参考译文。
值得说明的是，本公开中虽然以翻译语言为英文、原文为中文的案例进行举例，但是，本公开不对翻译的语言以及原文的语言进行限制，本公开中的原文还可以为中文文言文、译文可以为中文白话文，或者原文为日文、译文为英文等各种组合。
在一种可能的实施方式中，原文显示区域为可编辑区域，即原文显示区域中的文本内容可以编辑。基于此，该方法还包括响应于用户对所述原文显示区域中的文本内容进行修改的操作，更新所述译文区域内的参考译文。
在一些实施例中，文本内容“当铃声响起时，艾莉走进了学校”的参考译文为“When the bell rang,Allie entered the school.”，在接收到用户对原文显示区域中的文本内容“学校”修改为“教室”之后，可以更新译文区域中的参考译文为“When the bell rang,Allie entered the classroom.”
在一种可能的实施方式中，可以将所述待翻译文档内的文本内容分段，得到多个分段内容，针对每一所述分段内容，显示对应的原文显示区域、译文区域以及编辑区域。其中，所述原文显示区域显示有对应的分段内容，所述译文区域显示有对应的分段内容的参考译文。
在一些实现方式中，可以由用户手动对文本内容进行分段。例如，在需要分段的位置插入分段符。也可以根据所述待翻译文档内的文本内容的语义信息和/或分段符信息，对所述文本内容分段。例如，可以通过语意分段模型根据文字内容进行分段，将同语意的句子作为一个自然段显示。可选地，还可以在图片文档中的文字分布满足预设格式时按预设方式进行分段。例如，一个图片文档中的文字呈多处聚集式排列，则可以将该图片文档中的文字识别，并将在图片中处于相同位置的文字作为一个段落显示。
如图2所示的一种可能的翻译界面的示意图。其中，待翻译文档的文本内容在原文显示区域中显示，该原文显示区域显示在译文区域及编辑区域的上方，且不同的段落有不同的展示原文显示区域、译文区域以及编辑区域。每一段落的各个区域可以独立翻译，不因 其他区域的修改而更新。用户可以在编辑区域输入译文，或修改原文显示区域中的文本内容。
如图2的下方段落2的展示框中所示。在一种可能的实施方式中，可以在响应于用户对段落的选择操作显示编辑区域，在用户选中该段落之前隐藏该编辑区域。
如图3所示的一种可能的翻译界面的示意图。如图3最上方区域所示，原文显示区域可以位于译文区域以及编辑区域上方。在获取到文本内容后，可以对文本内容进行翻译，并将参考译文显示在译文区域，并跟随用户在编辑区域内的输入，在编辑区域中提供来自参考译文的译文建议。其中，已作为译文结果确认的译文建议，或用户已输入的译文用加粗字体显示，正在展示的译文建议以灰色普通字体显示。如图3中间区域所示，检测到用户在编辑区域中输入译文的非确认操作(如在编辑区域中输入不同于译文建议的译文)，根据用户输入的译文(加粗且下划线显示的字符为用户输入的字符)更新参考译文，并向用户展示来自更新后的参考译文的译文建议。如图3最下方区域所示，在用户采用该来自更新后的参考译文的译文建议后，该译文建议作为译文结果显示到编辑区域。用户编辑了原文显示区域的文本内容(加粗且下划线显示的文字为用户修改的文字)，则基于用户编辑的文本内容更新参考译文，并提供来自参考译文的译文建议。
在一种可能的实施方式中，可以将所述文本内容以及用户对所述文本内容的翻译结果作为训练样本，所述训练样本用于训练用户对应的深度学习翻译模型，以对所述深度学习翻译模型进行更新，以使深度学习翻译模型更符合用户的使用习惯。例如，用户习惯将单词“电话”翻译为“phone”而非“telephone”，则在用户多次使用之后，可以基于用户的翻译结果更新该用户对应的深度学习翻译模型，从而在后续使用时，将单词“电话”翻译为“phone”而非“telephone”，使其更符合该用户的使用习惯。
在一种可能的实施方式中，可以将翻译结果导出为用户指定的文档格式的翻译文档，并向用户提供下载服务。该方法还可以根据用户上传的待翻译文档中的排版格式，生成与该排版格式一致的翻译文档，从而达到节省用户排版时间的效果。例如，待翻译文档中的页边距为上部3厘米，下部2.5厘米，左部2.8厘米，右部2厘米，且标题大小为黑体二号字居中，副标题为黑体三号字，正文为中文宋体四号字，则在生成翻译文档时，可以将页边距与待翻译文档设置为一致，且将标题的文本内容对应的翻译结果调整为黑体二号字居中，副标题的文本内容调整为黑体三号字，正文调整为默认英文字体四号字，并将分段格式、回车数量、页码、页眉等调整为与待翻译文档一致，并导出为用户指定的文档格式，如word、pdf等。
基于上述的技术方案，至少可以达到以下技术效果：可以根据用户的输入提供来自参考译文的译文建议，并且，用户可以通过确认操作直接将译文建议作为译文结果，减少用户的输入时间，本公开结合人工的准确性及机器的高效性，可以提升翻译的效率以及翻译的质量。
图4是根据一示例性公开实施例示出的一种文档翻译装置的框图，如图4所示，所述文档翻译装置400包括：
展示模块410，用于展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文。
建议模块420，用于跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议。
所述建议模块420，还用于在检测到用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域，或者，在检测到用户针对所述译文建议的非确认操作的情况下，接收用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。
可选地，所述建议模块还用于根据用户输入的所述译文更新所述译文区域中的参考译文。
可选地，所述建议模块还包括显示子模块，用于在所述译文区域突出显示来自所述参考译文的译文建议，并在检测到用户针对所述译文建议的确认操作的情况下，取消所述译文建议在所述译文区域的突出显示。
可选地，所述显示子模块，用于在所述编辑区域以不同于已输入译文的显示方式来显示所述译文建议，并在检测到用户针对所述译文建议的确认操作的情况下，以与已输入译文的显示方式相同的方式来在所述编辑区域内显示作为译文结果的所述译文建议。
可选地，所述译文建议包括词、词组、句子中的至少一项
可选地，所述建议模块，还用于响应于用户对电子设备上的快捷键的触发操作，将所述译文建议作为译文结果显示到所述编辑区域。
可选地，所述装置还包括修改模块，用于响应于用户对所述原文显示区域中的文本内容进行修改的操作，更新所述译文区域内的参考译文。
可选地，所述展示模块还包括分段子模块，用于将所述待翻译文档内的文本内容分段，得到多个分段内容；所述展示模块，还用于针对每一所述分段内容，显示对应的原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域显示有对应的分段内容，所述译文区域显示有对应的分段内容的参考译文。
可选地，所述分段子模块，用于根据所述待翻译文档内的文本内容的语义信息和/或分段符信息，对所述文本内容分段，得到多个分段内容。
上述各模块的功能在上一实施例中的方法步骤中已详细阐述，在此不做赘述。
基于上述的技术方案，至少可以达到以下技术效果：可以根据用户的输入提供来自参考译文的译文建议，并且，用户可以通过确认操作直接将译文建议作为译文结果，减少用户的输入时间，本公开结合人工的准确性及机器的高效性，可以提升翻译的效率以及翻译的质量。
下面参考图5，其示出了适于用来实现本公开实施例的电子设备(例如图1中的终端设备或服务器)500的结构示意图。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP (便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图5示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图5所示，电子设备500可以包括处理装置(例如中央处理器、图形处理器等)501，其可以根据存储在只读存储器(ROM)502中的程序或者从存储装置508加载到随机访问存储器(RAM)503中的程序而执行各种适当的动作和处理。在RAM 503中，还存储有电子设备500操作所需的各种程序和数据。处理装置501、ROM 502以及RAM 503通过总线504彼此相连。输入/输出(I/O)接口505也连接至总线504。
通常，以下装置可以连接至I/O接口505：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置506；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置507；包括例如磁带、硬盘等的存储装置508；以及通信装置509。通信装置509可以允许电子设备500与其他设备进行无线或有线通信以交换数据。虽然图5示出了具有各种装置的电子设备500，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置509从网络上被下载和安装，或者从存储装置508被安装，或者从ROM 502被安装。在该计算机程序被处理装置501执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意 形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文；跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议；其中，在检测到所述用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域，或者，在检测到所述用户针对所述译文建议的非确认操作的情况下，接收所述用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言——诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块的名称在某种情况下并不构成对该模块本身的限定，例如，展示模块还可以被描述为“展示原文显示区域、译文区域以及编辑区域的模块”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，示例1提供了一种文档翻译方法，包括展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文；跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议；其中，在检测到用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域；在检测到用户针对所述译文建议的非确认操作的情况下，接收用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。
根据本公开的一个或多个实施例，示例2提供了示例1的方法，所述方法还包括：根据所述用户输入的所述译文更新所述译文区域中的参考译文。
根据本公开的一个或多个实施例，示例3提供了示例1的方法，所述提供来自所述参考译文的译文建议包括：在所述译文区域突出显示来自所述参考译文的译文建议；所述方法还包括：在检测到用户针对所述译文建议的确认操作的情况下，取消所述译文建议在所述译文区域的突出显示。
根据本公开的一个或多个实施例，示例4提供了示例3的方法，所述提供来自所述参考译文的译文建议包括：在所述编辑区域以不同于已输入译文的显示方式来显示所述译文建议；并且在检测到所述用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域包括：在检测到所述用户针对所述译文建议的确认操作的情况下，以与已输入译文的显示方式相同的方式来在所述编辑区域内显示作为译文结果的所述译文建议。
根据本公开的一个或多个实施例，示例5提供了示例1的方法，所述译文建议包括词、词组、句子中的至少一项。
根据本公开的一个或多个实施例，示例6提供了示例1的方法，所述在检测到用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域，包括：响应于用户对电子设备上的快捷键的触发操作，将所述译文建议作为译文结果显示到所述编辑区域。
根据本公开的一个或多个实施例，示例7提供了示例1-6的方法，所述方法还包括：响应于用户对所述原文显示区域中的文本内容进行修改的操作，更新所述译文区域内的参考译文。
根据本公开的一个或多个实施例，示例8提供了示例1-6的方法，所述展示原文显示区域、译文区域以及编辑区域，包括：将所述待翻译文档内的文本内容分段，得到多个分段内容；针对每一所述分段内容，显示对应的原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域显示有对应的分段内容，所述译文区域显示有对应的分段内容的参考译文。
根据本公开的一个或多个实施例，示例9提供了示例8的方法，所述将所述待翻译文档内的文本内容分段，得到多个分段内容，包括：根据所述待翻译文档内的文本内容的语义信息和/或分段符信息，对所述文本内容分段，得到多个分段内容。
根据本公开的一个或多个实施例，示例10提供了一种文档翻译装置，包括展示模块，用于展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文；建议模块，用于跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议；所述建议模块420，还用于在检测到用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域，并在检测到用户针对所述译文建议的非确认操作的情况下，接收用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。
根据本公开的一个或多个实施例，示例11提供了示例10的装置，所述建议模块还用于根据所述用户输入的所述译文更新所述译文区域中的参考译文。
根据本公开的一个或多个实施例，示例12提供了示例10的装置，所述建议模块还包括显示子模块，用于在所述译文区域突出显示来自所述参考译文的译文建议，并在检测到用户针对所述译文建议的确认操作的情况下，取消所述译文建议在所述译文区域的突出显示。
根据本公开的一个或多个实施例，示例13提供了示例12的装置，所述显示子模块，用于在所述编辑区域以不同于已输入译文的显示方式来显示所述译文建议；在检测到所述用户针对所述译文建议的确认操作的情况下，以与已输入译文的显示方式相同的方式来在所述编辑区域内显示作为译文结果的所述译文建议。
根据本公开的一个或多个实施例，示例14提供了示例10的装置，所述译文建议包括词、词组、句子中的至少一项。
根据本公开的一个或多个实施例，示例15提供了示例10的装置，所述建议模块，还用于响应于用户对电子设备上的快捷键的触发操作，将所述译文建议作为译文结果显示到所述编辑区域。
根据本公开的一个或多个实施例，示例16提供了示例10-15的装置，所述装置还包括修改模块，用于响应于用户对所述原文显示区域中的文本内容进行修改的操作，更新所述译文区域内的参考译文。
根据本公开的一个或多个实施例，示例17提供了示例10-15的装置，所述展示模块还包括分段子模块，用于将所述待翻译文档内的文本内容分段，得到多个分段内容；所述展示模块，还用于针对每一所述分段内容，显示对应的原文显示区域、译文区域以及编辑区 域，其中，所述原文显示区域显示有对应的分段内容，所述译文区域显示有对应的分段内容的参考译文。
根据本公开的一个或多个实施例，示例18提供了示例117的装置，所述分段子模块，用于根据所述待翻译文档内的文本内容的语义信息和/或分段符信息，对所述文本内容分段，得到多个分段内容。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。

Claims (12)

  1. 一种文档翻译方法，其特征在于，所述方法包括：
    展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文；
    跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议；
    其中，在检测到所述用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域，或者，在检测到所述用户针对所述译文建议的非确认操作的情况下，接收所述用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    根据所述用户输入的所述译文更新所述译文区域中的参考译文。
  3. 根据权利要求1所述的方法，其特征在于，所述提供来自所述参考译文的译文建议包括：
    在所述译文区域突出显示来自所述参考译文的译文建议；
    所述方法还包括：在检测到所述用户针对所述译文建议的确认操作的情况下，取消所述译文建议在所述译文区域的突出显示。
  4. 根据权利要求1所述的方法，其特征在于，提供来自所述参考译文的译文建议包括：
    在所述编辑区域以不同于已输入译文的显示方式来显示所述译文建议；
    并且在检测到所述用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域包括：
    在检测到所述用户针对所述译文建议的确认操作的情况下，以与已输入译文的显示方式相同的方式来在所述编辑区域内显示作为译文结果的所述译文建议。
  5. 根据权利要求1所述的方法，其特征在于，所述译文建议包括词、词组、句子中的至少一项。
  6. 根据权利要求1所述的方法，其特征在于，所述在检测到所述用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域，包括：
    响应于用户对电子设备上的快捷键的触发操作，将所述译文建议作为译文结果显示到所述编辑区域。
  7. 根据权利要求1-6任一项所述的方法，其特征在于，所述方法还包括：
    响应于所述用户对所述原文显示区域中的文本内容进行修改的操作，更新所述译文区域内的参考译文。
  8. 根据权利要求1-6任一项所述的方法，其特征在于，所述展示原文显示区域、译文区域以及编辑区域，包括：
    将所述待翻译文档内的文本内容分段，得到多个分段内容；
    针对每一所述分段内容，显示对应的原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域显示有对应的分段内容，所述译文区域显示有对应的分段内容的参考译文。
  9. 根据权利要求8所述的方法，其特征在于，所述将所述待翻译文档内的文本内容分段，得到多个分段内容，包括：
    根据所述待翻译文档内的文本内容的语义信息和/或分段符信息，对所述文本内容分段，得到多个分段内容。
  10. 一种文档翻译装置，其特征在于，所述装置包括：
    展示模块，用于展示原文显示区域、译文区域以及编辑区域，其中，所述原文显示区域中显示有待翻译文档中的文本内容，所述译文区域中显示有对所述文本内容的参考译文；
    建议模块，用于跟随用户在所述编辑区域内的输入，提供来自所述参考译文的译文建议；
    所述建议模块，还用于在检测到所述用户针对所述译文建议的确认操作的情况下，将所述译文建议作为译文结果显示到所述编辑区域，或者，在检测到所述用户针对所述译文建议的非确认操作的情况下，接收所述用户输入的不同于所述译文建议的译文，将所述用户输入的所述译文作为所述译文结果显示到所述编辑区域。
  11. 一种计算机可读介质，其上存储有计算机程序，其特征在于，该程序被处理装置执行时实现权利要求1至9中任一项所述方法的步骤。
  12. 一种电子设备，其特征在于，包括：
    存储装置，其上存储有计算机程序；
    处理装置，用于执行所述存储装置中的所述计算机程序，以实现权利要求1至9中任一项所述方法的步骤。
PCT/CN2021/099109 2020-06-23 2021-06-09 文档翻译方法和装置、存储介质和电子设备 WO2021259061A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2022545064A JP2023511971A (ja) 2020-06-23 2021-06-09 ドキュメント翻訳方法及び装置、記憶媒体並びに電子デバイス
KR1020227029309A KR20220123736A (ko) 2020-06-23 2021-06-09 문서 번역 방법 및 장치, 저장 매체 및 전자 디바이스
EP21828949.4A EP4083849A4 (en) 2020-06-23 2021-06-09 METHOD AND APPARATUS FOR TRANSLATING DOCUMENT, STORAGE MEDIA AND ELECTRONIC DEVICE
US17/872,966 US11580314B2 (en) 2020-06-23 2022-07-25 Document translation method and apparatus, storage medium, and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010584747.1 2020-06-23
CN202010584747.1A CN111666776B (zh) 2020-06-23 2020-06-23 文档翻译方法和装置、存储介质和电子设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/872,966 Continuation US11580314B2 (en) 2020-06-23 2022-07-25 Document translation method and apparatus, storage medium, and electronic device

Publications (1)

Publication Number Publication Date
WO2021259061A1 true WO2021259061A1 (zh) 2021-12-30

Family

ID=72389796

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/099109 WO2021259061A1 (zh) 2020-06-23 2021-06-09 文档翻译方法和装置、存储介质和电子设备

Country Status (6)

Country Link
US (1) US11580314B2 (zh)
EP (1) EP4083849A4 (zh)
JP (1) JP2023511971A (zh)
KR (1) KR20220123736A (zh)
CN (1) CN111666776B (zh)
WO (1) WO2021259061A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111666776B (zh) 2020-06-23 2021-07-23 北京字节跳动网络技术有限公司 文档翻译方法和装置、存储介质和电子设备
CN112417898A (zh) * 2020-11-24 2021-02-26 掌阅科技股份有限公司 基于关键词提示的文本翻译方法、计算设备及存储介质
CN112633015A (zh) * 2020-12-30 2021-04-09 语联网（武汉）信息技术有限公司 文档翻译方法、装置、电子设备及存储介质
WO2022224057A1 (en) * 2021-04-20 2022-10-27 Deeptranslate Limited Machine translation guided by reference documents
CN115345180A (zh) * 2021-05-14 2022-11-15 阿里巴巴新加坡控股有限公司 数据处理方法、装置、电子设备和存储介质
CN113703890B (zh) * 2021-08-11 2023-10-20 百度在线网络技术（北京）有限公司 显示控制方法、装置、电子设备和存储介质
CN113625922B (zh) * 2021-10-11 2023-02-28 统信软件技术有限公司 一种文件翻译方法、计算设备及可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007068960A2 (en) * 2005-12-16 2007-06-21 Emil Ltd A text editing apparatus and method
CN101382935A (zh) * 2007-09-06 2009-03-11 英业达股份有限公司 提供输入编辑后的翻译词句的系统及其方法
CN104714943A (zh) * 2015-03-26 2015-06-17 百度在线网络技术（北京）有限公司 翻译方法及系统
CN107885729A (zh) * 2017-09-25 2018-04-06 沈阳航空航天大学 基于双语片段的交互式机器翻译方法
CN111666776A (zh) * 2020-06-23 2020-09-15 北京字节跳动网络技术有限公司 文档翻译方法和装置、存储介质和电子设备

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6244874A (ja) * 1985-08-22 1987-02-26 Toshiba Corp 機械翻訳装置
JPS6244877A (ja) * 1985-08-22 1987-02-26 Toshiba Corp 機械翻訳装置
JPS62163173A (ja) * 1986-01-14 1987-07-18 Toshiba Corp 機械翻訳方法
JPS62203273A (ja) * 1986-03-04 1987-09-07 Toshiba Corp 機械翻訳システム
US5349368A (en) * 1986-10-24 1994-09-20 Kabushiki Kaisha Toshiba Machine translation method and apparatus
JPH02140868A (ja) * 1988-11-22 1990-05-30 Toshiba Corp 機械翻訳システム
US5608622A (en) * 1992-09-11 1997-03-04 Lucent Technologies Inc. System for analyzing translations
US6598015B1 (en) * 1999-09-10 2003-07-22 Rws Group, Llc Context based computer-assisted language translation
US7536294B1 (en) * 2002-01-08 2009-05-19 Oracle International Corporation Method and apparatus for translating computer programs
WO2004081813A1 (ja) * 2003-03-14 2004-09-23 Fujitsu Limited 翻訳支援装置
US20080147378A1 (en) * 2006-12-08 2008-06-19 Hall Patrick J Online computer-aided translation
US8635539B2 (en) * 2008-10-31 2014-01-21 Microsoft Corporation Web-based language translation memory compilation and application
US9767095B2 (en) * 2010-05-21 2017-09-19 Western Standard Publishing Company, Inc. Apparatus, system, and method for computer aided translation
US9183198B2 (en) * 2013-03-19 2015-11-10 International Business Machines Corporation Customizable and low-latency interactive computer-aided translation
JP6226321B2 (ja) * 2013-10-23 2017-11-08 株式会社サン・フレア 翻訳支援システム、翻訳支援システムのサーバー、翻訳支援システムのクライアント、翻訳支援システムの制御方法、及びそのプログラム
JP6250013B2 (ja) * 2014-11-26 2017-12-20 ネイバー コーポレーションＮＡＶＥＲ Ｃｏｒｐｏｒａｔｉｏｎ コンテンツ参加翻訳装置、及びそれを利用したコンテンツ参加翻訳方法
WO2016185289A1 (en) * 2015-05-21 2016-11-24 Gammakite, Llc Device for language teaching with time dependent data memory
US10235007B2 (en) * 2015-05-21 2019-03-19 Gammakite, Llc Guided operation of a language device based on constructed, time-dependent data structures
EP3436971A4 (en) * 2016-04-20 2019-12-04 Google LLC AUTOMATIC TRANSLATIONS BY KEYBOARD
US10394965B2 (en) * 2017-01-13 2019-08-27 Sap Se Concept recommendation based on multilingual user interaction
JP2019091361A (ja) * 2017-11-16 2019-06-13 株式会社Ｉ．Ｍｅｉｓｔｅｒｓ 翻訳支援装置、翻訳支援プログラム、および情報処理装置により翻訳を支援する方法
CN110162798B (zh) * 2018-08-09 2022-05-20 腾讯科技（深圳）有限公司 文档翻译方法、装置、计算机可读存储介质和计算机设备
KR20210041007A (ko) * 2018-08-29 2021-04-14 유장현 특허 문서 작성 장치, 방법, 컴퓨터 프로그램, 컴퓨터로 판독 가능한 기록매체, 서버 및 시스템
CN109710948A (zh) * 2018-11-27 2019-05-03 语联网（武汉）信息技术有限公司 机器翻译引擎推荐方法及装置
KR102390187B1 (ko) * 2020-05-27 2022-04-25 네이버 주식회사 회의보조용 번역 도구를 위한 방법 및 시스템

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007068960A2 (en) * 2005-12-16 2007-06-21 Emil Ltd A text editing apparatus and method
CN101382935A (zh) * 2007-09-06 2009-03-11 英业达股份有限公司 提供输入编辑后的翻译词句的系统及其方法
CN104714943A (zh) * 2015-03-26 2015-06-17 百度在线网络技术（北京）有限公司 翻译方法及系统
CN107885729A (zh) * 2017-09-25 2018-04-06 沈阳航空航天大学 基于双语片段的交互式机器翻译方法
CN111666776A (zh) * 2020-06-23 2020-09-15 北京字节跳动网络技术有限公司 文档翻译方法和装置、存储介质和电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4083849A4

Also Published As

Publication number Publication date
JP2023511971A (ja) 2023-03-23
US11580314B2 (en) 2023-02-14
CN111666776A (zh) 2020-09-15
CN111666776B (zh) 2021-07-23
US20220374617A1 (en) 2022-11-24
EP4083849A4 (en) 2023-07-12
KR20220123736A (ko) 2022-09-08
EP4083849A1 (en) 2022-11-02

Similar Documents

Publication Publication Date Title
WO2021259061A1 (zh) 文档翻译方法和装置、存储介质和电子设备
WO2019214365A1 (zh) 翻译模型训练的方法、语句翻译的方法、设备及存储介质
JP5449633B1 (ja) 広告翻訳装置、広告表示装置、および広告翻訳方法
US11954455B2 (en) Method for translating words in a picture, electronic device, and storage medium
WO2021259221A1 (zh) 视频翻译方法和装置、存储介质和电子设备
CN111339788B (zh) 交互式机器翻译方法、装置、设备和介质
CN111563390B (zh) 文本生成方法、装置和电子设备
US20180239743A1 (en) Keyboard input corresponding to multiple languages
CN111898388A (zh) 视频字幕翻译编辑方法、装置、电子设备及存储介质
WO2023016391A1 (zh) 多媒体数据的生成方法、装置、可读介质及电子设备
CN111860000A (zh) 文本翻译编辑方法、装置、电子设备及存储介质
CN111783508A (zh) 用于处理图像的方法和装置
WO2023143071A2 (zh) 内容展示方法、装置、电子设备及存储介质
WO2022174804A1 (zh) 文本简化方法、装置、设备及存储介质
EP4195011A1 (en) Character display method and apparatus, and electronic device and computer-readable storage medium
CN111291575B (zh) 文本处理方法、装置、电子设备、及存储介质
JP7179512B2 (ja) 情報処理方法、情報処理装置、及びプログラム
CN115357160B (zh) 文档内容点选方法、装置、电子设备、介质和程序产品
CN104850316A (zh) 电子图书字体调整方法及装置
CN115344718B (zh) 跨区域文档内容识别方法、装置、设备、介质和程序产品
CN118133841A (zh) 文本处理方法及装置、计算机可读存储介质和电子设备
CN114697760A (zh) 一种处理方法、装置、电子设备及介质
KR20220006357A (ko) 저시력자를 위한 웹문서 제공방법 및 그 사용자 단말
CN111899575A (zh) 听写内容发布方法、装置、设备和存储介质
CN111368561A (zh) 平行语料获取方法、装置、电子设备、及存储介质

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: 21828949

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022545064

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20227029309

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2021828949

Country of ref document: EP

Effective date: 20220725

NENP Non-entry into the national phase

Ref country code: DE