CN108399166A - Text interpretation method, device, computer equipment and storage medium - Google Patents
Text interpretation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108399166A CN108399166A CN201810124553.6A CN201810124553A CN108399166A CN 108399166 A CN108399166 A CN 108399166A CN 201810124553 A CN201810124553 A CN 201810124553A CN 108399166 A CN108399166 A CN 108399166A
- Authority
- CN
- China
- Prior art keywords
- text
- translation
- party
- source
- interface
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
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
- G06F40/58—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
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
Abstract
This application involves a kind of text interpretation method, device, computer equipment and storage mediums.The method includes：Obtain the address of source text in Content Management System；Source text corresponding with described address is called by the first interface that the Content Management System provides；By the second interface docked with third party's translation system, the source text of calling is sent to third party's translation system；By the second interface, the machine translation text corresponding with the source text of third party's translation system feedback is received；Text exhibition editing interface, and machine translation text of the displaying in editable state in the text editing interface；According to the edit operation for acting on the text editing interface, the machine translation text of displaying is calibrated.Text translation efficiency can be improved using this method.
Description
Technical field
This application involves machine translation mothod fields, more particularly to a kind of text interpretation method, device, computer equipment
And storage medium.
Background technology
With the development of network technology, there is machine translation mothod, machine translation is to utilize computer by a kind of language
Translate into another language.In many career fields, can usually it involve the need for a kind of content translation of language at several
The case where language of country variant.Such as multilingual webpage development, it is often necessary to which the content of webpage need to be translated into several differences
The case where language of country is presented.For needing to turn over a kind of content translation of language at the text of the language of several country variants
Method is translated, traditional way is by the background management system of text to be translated, and inquiry needs the particular content translated, then need to
The content to be translated copies in third party's translation system, is translated by third party's translation system, by the word after translation
Background management system of the copying and saving in text to be translated.
But based on traditional interpretation method, often refer to carry out carrying out switchback between multiple browser labels in operating process
It changes, operation is easy to happen entanglement, and due to logging in the limitations such as timeliness, translates data for a long time and is easy to cause process failure,
And then data is caused to preserve failure, cause translation efficiency low.
Invention content
Based on this, it is necessary in view of the above technical problems, provide a kind of text interpretation method that can improve translation efficiency,
Device, computer equipment and storage medium.
A kind of text interpretation method, the method includes：Obtain the address of source text in Content Management System；By described
The first interface that Content Management System provides calls source text corresponding with described address；By with third party's translation system pair
The source text of calling is sent to third party's translation system by the second interface connect；By the second interface, receive
The machine translation text corresponding with the source text of third party's translation system feedback；Text exhibition editing interface, and
Machine translation text of the displaying in editable state in the text editing interface；According to acting on the text editing interface
Edit operation, calibrate the machine translation text of displaying.
The address for obtaining source text in Content Management System in one of the embodiments, including：The first text of displaying
This label；When detecting the operation for choosing first text label, address model corresponding with first text label is determined
Enclose included address；Described address is used to position the source text in the Content Management System；Displaying is using described address as chain
The second text label connect；When detecting the operation for choosing second text label, the second text label institute chosen is obtained
The address of link.
The text exhibition editing interface in one of the embodiments, and in the text editing interface at displaying
Before the machine translation text of editable state, the method further includes：Whole sentence is isolated from the machine translation text；
The whole sentence is inputted into the machine learning model trained, obtains the grammatical feature unit isolated from the whole sentence；According to
The corresponding default linguistic constraints condition of the grammatical feature unit, identifies the grammatical feature unit of translation error and corrects, obtain
Revised machine translation text.
In one of the embodiments, by the second interface docked with third party's translation system, by the source of calling
Text was sent to before the step of third party's translation system, and the method further includes：By the file format of the source text
It is converted into the file format to match with third party's translation system；Second the connecing by being docked with third party's translation system
Mouthful, the source text of calling, which is sent to third party's translation system, includes：Pass through what is docked with third party's translation system
Source text after convert file formats is sent to third party's translation system by second interface；It is described to be connect by described second
Mouthful, it is described after the step of receiving the machine translation text corresponding with the source text of third party's translation system feedback
Method further includes：The file format of the machine translation text of reception is converted into the file format of the source text.
The method further includes in one of the embodiments,：Obtain in the Content Management System with described address phase
Corresponding cypher text storage address；According to the cypher text storage address, the machine translation text of the displaying will be calibrated
The cypher text obtained afterwards is stored into the Content Management System.
The source text is the web page contents in the webpage of the first languages in one of the embodiments,；The method is also
Including：Obtain the web page template of the webpage of first languages；The position corresponding with the source text in the web page template
Place adds the cypher text obtained by calibration corresponding with the source text, generates the webpage of the second languages.
A kind of text translating equipment, described device include：Acquisition module, for obtaining source text in Content Management System
Address；Calling module, the first interface for being provided by the Content Management System call source corresponding with described address
Text；The source text of calling is sent to by sending module for the second interface by being docked with third party's translation system
Third party's translation system；Receiving module, for by the second interface, receiving third party's translation system feedback
Machine translation text corresponding with the source text；Display module is used for text exhibition editing interface, and in the text editing
Machine translation text of the displaying in editable state in interface；Calibration module acts on text editing circle for basis
The machine translation text of displaying is calibrated in the edit operation in face.
Described device further includes in one of the embodiments,：Separation module, for dividing from the machine translation text
Separate out whole sentence；Input module obtains detaching from the whole sentence for the whole sentence to be inputted the machine learning model trained
The grammatical feature unit gone out；Correcting module, for according to the corresponding default linguistic constraints condition of the grammatical feature unit, identification
The grammatical feature unit of translation error is simultaneously corrected, and revised machine translation text is obtained.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes the text interpretation method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of text interpretation method is realized when row.
Above-mentioned text interpretation method, device, computer equipment and storage medium, first provided by Content Management System
Interface can directly invoke source text corresponding with the address of source text in Content Management System, then be by being translated with third party
Source text is sent to third party's translation system by the second interface of system docking, can realize the machine translation process of source text automatically,
Without manually being toggled in multiple browser labels, reduces During manual operation, improve translation efficiency.Again
According to text editing interface is acted on, it is directed to the edit operation of machine translation text, calibration machine cypher text can carry
Translation quality has been ensured on the basis of high translation efficiency.In this way, carrying out machine translation by third party's translation system combines editor
The mode of calibration translates source text, it is possible to reduce During manual operation reduces error probability, and to machine translation text
This is calibrated to ensure the quality of translation, is reduced rework rate, is further improved text translation efficiency.
Description of the drawings
Fig. 1 is the application scenario diagram of text interpretation method in one embodiment；
Fig. 2 is the flow diagram of text interpretation method in one embodiment；
Fig. 3 is flow diagram the step of obtaining the address of source text in Content Management System in one embodiment；
Fig. 4 is the flow diagram for the step of grammatical feature unit is corrected in one embodiment；
Fig. 5 is the flow diagram of text interpretation method in another embodiment；
Fig. 6 is the structure diagram of text translating equipment in one embodiment；
Fig. 7 is the structure diagram of text translating equipment in another embodiment；
Fig. 8 is the structure diagram of text translating equipment in another embodiment；
Fig. 9 is the internal structure chart of one embodiment Computer equipment.
Specific implementation mode
It is with reference to the accompanying drawings and embodiments, right in order to make the object, technical solution and advantage of the application be more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Text interpretation method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, terminal 110
It is communicated by interface with Content Management System 120, terminal 110 is communicated with third party's translation system 130 by interface.
Wherein, terminal 110 can be, but not limited to be various personal computers, laptop, smart mobile phone, tablet computer and portable
Wearable device etc., Content Management System 120 can use the server set of the either multiple server compositions of independent server
Group realizes.
In one embodiment, as shown in Fig. 2, providing a kind of text interpretation method, it is applied in Fig. 1 in this way
It illustrates, includes the following steps for terminal：
S202 obtains the address of source text in Content Management System.
Wherein, Content Management System is a kind of positioned at Web (World Wide Web, global wide area network) front-end and back-end system
Software systems between system or flow.Various data, such as text file, HTML are stored in the content library of Content Management System
The data of (Hyper Text Markup Language, HyperText Markup Language) webpage, Web service, relational database etc..
Content Management System such as CMS (Content Management System, Content Management System).Source text is to be translated
Text can be specifically the word content or data of the file to be translated stored with formats such as word, excel or txt
The word content etc. stored in library.
In one embodiment, supplementary translation application can be installed in terminal.After running supplementary translation application, turned in auxiliary
Address input box can be shown by translating on the display interface of application.Terminal can directly acquire the address being input in address input box,
Wherein, address is the address of source text in Content Management System.
In one embodiment, after terminal operating supplementary translation application, supplementary translation application can voluntarily scans content management
All Files in system.The Text Flag that can be shown on display interface and indicate different source texts, this article are applied in supplementary translation
This mark links to the address of the source text.Terminal is directed to the trigger action of Text Flag by receiving, and can obtain the text
Identify the address of link.
In one embodiment, terminal can show the first text label in supplementary translation application.Wherein, text label is
The label of text can identify the text.First text label such as text categories label.Terminal detect choose first text
When the operation of this label, the address included by address range corresponding with the first text label is determined.Terminal, which detects, chooses
After the operation of one text label, it can show that multiple addresses in above-mentioned address range are the second text label of link.Second
Text label such as Text Flag.When terminal detects the operation for choosing the second text label, the second text mark chosen is obtained
The linked address of label.
In one embodiment, terminal obtains behind the address inputted in the address input box that supplementary translation is applied, determines
The Text Flag of source text corresponding to the address of the acquisition either the second text label and by Text Flag or the second text
Label is added to the Text Flag of supplementary translation application or the display interface of text label.
S204 calls source text corresponding with address by the first interface that Content Management System provides.
Wherein, interface is the Border that two independent components carry out information exchange in computer system.Such as API
(Application Programming Interface, System Programming interface) interface.Wherein, API is that some are pre-defined
Function, it is therefore an objective to the ability that the system that provides is based on one group of routine of access of certain software (or hardware), and without access software
Source code, or understand the details of the internal work mechanism of software.The first interface that Content Management System provides can be specifically that API connects
Mouthful.
Specifically, terminal behind the address of source text, can be carried in getting Content Management System by Content Management System
The first interface of confession, such as api interface pass through supplementary translation application API Calls source text corresponding with the address of acquisition.
In one embodiment, when supplementary translation is applied through API Calls source text, source text has N row, can assist
The columns that need to be translated, the source text that need to be translated with accurately determination are selected in the source text selection interface of translation application.
In one embodiment, source text can be included the source document applied in supplementary translation after obtaining source text by terminal
In this display interface.
The source text of calling is sent to third party and is turned over by S206 by the second interface docked with third party's translation system
Translate system.
Specifically, terminal can will be called after obtaining source text by the second interface docked with third party's translation system
Source text be sent to third party's translation system.Wherein, third party's translation system such as Netease's translation system, Google's translation system
Or Baidu's translation system etc..
In one embodiment, terminal is after obtaining source text, can be converted into the file format of source text and third party
The file format that translation system matches, then the second interface by being docked with third party's translation system, by convert file formats
Source text afterwards is sent to third party's translation system.
S208 receives the machine translation text corresponding with source text of third party's translation system feedback by second interface.
Specifically, after source text is sent to third party's translation system by terminal, third party's translation system can be to source file
Carry out machine translation.Third party's translation system is by the machine translation text feedback after machine translation to terminal.Terminal passes through second
Interface receives the machine translation text corresponding with source text of third party's translation system feedback.
In one embodiment, can include in supplementary translation by machine translation text after terminal receiver device cypher text
Cypher text display interface in.Wherein, source text display interface and cypher text display interface can be shown in end side by side
In the display interface at end, for example, the left and right side of terminal, source text and cypher text are checked in order to compare.Further,
Cypher text and source text can be shown in which correspond in respective display interface.Wherein, it shows with corresponding, such as with
Whole sentence is unit, and cypher text and the mutual corresponding whole sentence of source text are shown in the corresponding position in respective display interface.
S210, text exhibition editing interface, and machine translation of the displaying in editable state in text editing interface
Text.
Specifically, terminal can text exhibition editing interface, third party's translation system of reception is fed back and source text phase
The machine translation textual presentation answered is in text editing interface.Machine translation text shown in text editing interface is in and can compile
The state of collecting.
S212 calibrates the machine translation text of displaying according to the edit operation for acting on text editing interface.
Specifically, terminal can receive the edit operation for acting on text editing interface, according to edit operation to the machine of displaying
Device cypher text is calibrated, with the cypher text after being calibrated.
Above-mentioned text interpretation method, the first interface provided by Content Management System can directly invoke and Content Management system
The corresponding source text in the address of source text in system, then the second interface by being docked with third party's translation system send out source text
It send to third party's translation system, can realize the machine translation process of source text automatically, without manually in multiple browsers
It is toggled in label, reduces During manual operation, improve translation efficiency.Further according to acting on text editing interface,
It is directed to the edit operation of machine translation text, calibration machine cypher text can ensure on the basis of improving translation efficiency
Translation quality.In this way, third party's translation system turn over source text by way of machine translation combines editor's calibration
It translates, it is possible to reduce During manual operation reduces error probability, and calibrated machine translation text to ensure the matter of translation
Amount reduces rework rate, further improves text translation efficiency.
In one embodiment, step S202 is specifically included：
S302 shows the first text label.
Specifically, supplementary translation application can be installed in terminal.After running supplementary translation application, in supplementary translation application
The first text label can be shown on display interface.First text label such as text categories label.
S304 when detecting the operation for choosing the first text label, determines address range corresponding with the first text label
Included address；Address is used to position the source text in Content Management System.
Specifically, terminal receive act on the first text label choose operation, marked according to choose operation to act on first
Label determine the address included by address range corresponding with the first text label.Wherein, address is for positioning Content Management System
In source text.
S306, displaying is with the second text label that address is link.
Specifically, terminal can be shown more after determining the address included by address range corresponding with the first text label
A address in above-mentioned address range is the second text label of link.Second text label such as Text Flag.
S308 when detecting the operation for choosing the second text label, obtains the ground that the second text label chosen is linked
Location.
Specifically, terminal receive act on the second text label choose operation, marked according to choose operation to act on second
Label, determine the address that the second text label is linked.
In above-described embodiment, by detect be directed in the first text label of displaying when choosing operation, determine with
The address included by the corresponding address range of the first text label chosen, displaying is with the second text mark that address above mentioned is link
Label.Thus the address that the second text label chosen is linked can be obtained by choosing the second text label, simplified
It is manually entered the operation of the address of source text, improves the acquisition efficiency of source text.
In one embodiment, before step S210, text interpretation method further includes the modified step of grammatical feature unit
Suddenly, which specifically includes：
S402 isolates whole sentence from machine cypher text.
Wherein, whole sentence is complete sentence.Specifically, terminal can determine machine according to the punctuation mark in machine translation text
Whole sentence in device cypher text, and whole sentence is isolated from machine cypher text.For example, terminal can detect in machine translation text
Fullstop, when detecting fullstop, by the previous machine translation text detected after fullstop and the machine before it time detect fullstop
Device cypher text is as a whole sentence.
Whole sentence is inputted the machine learning model trained, obtains the grammatical feature unit isolated from whole sentence by S404.
Wherein, machine learning model is machine learning algorithm model, is a kind of neural network model.Machine learning English is complete
Referred to as Machine Learning, abbreviation ML.The machine learning model trained is the machine with classification capacity after training
Device learning algorithm model.Grammatical feature unit be constitute the syntactic units as unit of syntactic structure of whole sentence, such as subject, meaning
Language, object etc..
Machine learning model in the present embodiment can be specifically Hidden Markov Model or CRF (conditional
Random field algorithm, condition random field algorithm) model etc..The sample number of machine learning model can be obtained in advance
According to being trained to machine learning model by sample data so that the machine learning model trained can carry out whole sentence
Grammatical feature unit identifies, and grammatical feature unit is isolated from whole sentence.
Specifically, whole sentence can be inputted the machine learning model trained by terminal, obtain the grammer isolated from whole sentence
Element unit.
S406 identifies the grammatical feature list of translation error according to the corresponding default linguistic constraints condition of grammatical feature unit
Member is simultaneously corrected, and revised machine translation text is obtained.
Wherein, it is pre-set linguistic constraints condition to preset linguistic constraints condition, corresponding with grammatical feature unit.It is default
It is predicate after linguistic constraints condition such as subject, not directly adds object；Only there are one predicates etc. in one whole sentence.
Specifically, terminal can identify the language of translation error according to the corresponding default linguistic constraints condition of grammatical feature unit
Method element unit, and the grammatical feature unit of mistake is automatically corrected, for example the wrong sequence of grammatical feature unit is adjusted,
Or delete extra grammatical feature unit etc..The grammatical feature unit of translation error in whole sentence in terminal-pair machine translation text
It is modified, obtains revised machine translation text.
In above-described embodiment, by the way that the whole sentence in machine translation text is inputted the machine learning model trained, obtain
The grammatical feature unit isolated from whole sentence identifies the grammatical feature list of translation error further according to default linguistic constraints condition
Member is simultaneously corrected, and can be carried out wrong identification and amendment automatically to machine translation text, be improved text translation efficiency.
In one embodiment, before step S206, text interpretation method further includes：The file format of source text is turned
Change the file format to match with third party's translation system into；Step S206 includes：Pass through what is docked with third party's translation system
Source text after convert file formats is sent to third party's translation system by second interface；After step S208, text translation
Method further includes：The file format of the machine translation text of reception is converted into the file format of source text.
Specifically, the file format of source text can be converted into and third party's translation system by terminal after calling source text
The file format to match, then the second interface by being docked with third party's translation system, by the source document after convert file formats
Originally it is sent to third party's translation system.In the machine translation text corresponding with source text for receiving third party's translation system feedback
Afterwards, the file format of the machine translation text of reception is converted into the file format of source text.
In above-described embodiment, terminal is by the way that the file format of source text to be converted into matching with third party's translation system
File format may be implemented to be docked with third party system automatically, so that third party's translation system can identify that source text is gone forward side by side
Row machine translation.Terminal sends source text by second interface and receives machine cypher text, can in text editing interface with
The file format of source text shows machine cypher text.
In one embodiment, text interpretation method further includes the steps that the step of text preserves, and the text preserves includes：
Obtain cypher text storage address corresponding with address in Content Management System；According to cypher text storage address, will calibrate
The cypher text obtained after the machine translation text of displaying is stored into Content Management System.
In one embodiment, it after terminal can detect cypher text preservation instruction, is applied in the supplementary translation of operation
Cypher text storage address input frame is shown on display interface.Terminal, which can directly acquire, is input to the input of cypher text storage address
The address of frame, wherein address is address corresponding with source text in Content Management System.The machine translation that terminal shows calibration
The third interface that the cypher text obtained after text is provided by Content Management System is stored into Content Management System.
In one embodiment, it after terminal can detect cypher text preservation instruction, is applied in the supplementary translation of operation
Cypher text storage address choice box is shown on display interface.Cypher text storage address choice box may include Content Management System
In multiple cypher text storage address.The cypher text obtained after the machine translation text of calibration displaying is passed through content by terminal
The third interface that management system provides is stored into Content Management System.
In above-described embodiment, terminal can store cypher text to specified translation text corresponding with the address of source text
This storage address can obtain source text and corresponding translation text when that need to use cypher text directly from Content Management System
This, it is convenient and efficient.
In one embodiment, source text is the web page contents in the webpage of the first languages；Text interpretation method further includes：
Obtain the web page template of the webpage of the first languages；In web page template at position corresponding with source text, addition and source text pair
The cypher text obtained by calibration answered generates the webpage of the second languages.
Wherein, web page template is multilingual webpage development in the process for the template of Reusability.Specifically, multilingual
In webpage development, terminal can obtain the web page template of the webpage of the first languages from server or terminal itself.In web page template
At position corresponding with source text, load renders the cypher text obtained by calibration corresponding with source text, generates the second language
The webpage of kind.
In above-described embodiment, when text interpretation method is applied to multilingual webpage development, source text is the first languages
Web page contents in webpage, terminal can add warp corresponding with source text in web page template at position corresponding with source text
The cypher text that calibration obtains is crossed, the webpage of the second languages is generated.Cypher text to be directly acquired from Content Management System logical in this way
The webpage that cypher text generates the second languages is crossed, the efficiency of multilingual webpage development is improved.
As shown in figure 5, in a specific embodiment, text interpretation method includes the following steps：
S502 shows the first text label.
S504 when detecting the operation for choosing the first text label, determines address range corresponding with the first text label
Included address；Address is used to position the source text in Content Management System.
S506, displaying is with the second text label that address is link.
S508 when detecting the operation for choosing the second text label, obtains the ground that the second text label chosen is linked
Location.
S510 calls source text corresponding with address by the first interface that Content Management System provides.
S512, the file format that the file format of source text is converted into matching with third party's translation system.
S514 is sent the source text after convert file formats by the second interface docked with third party's translation system
To third party's translation system.
S516 receives the machine translation text corresponding with source text of third party's translation system feedback by second interface.
The file format of the machine translation text of reception is converted into the file format of source text by S518.
S520 isolates whole sentence from machine cypher text.
Whole sentence is inputted the machine learning model trained, obtains the grammatical feature unit isolated from whole sentence by S522.
S524 identifies the grammatical feature list of translation error according to the corresponding default linguistic constraints condition of grammatical feature unit
Member is simultaneously corrected, and revised machine translation text is obtained.
S526, text exhibition editing interface, and machine translation of the displaying in editable state in text editing interface
Text.
S528 calibrates the machine translation text of displaying according to the edit operation for acting on text editing interface.
S530 obtains cypher text storage address corresponding with address in Content Management System.
S532 deposits the cypher text obtained after the machine translation text of calibration displaying according to cypher text storage address
In storage to Content Management System.
S534 obtains the web page template of the webpage of the first languages.
S536, in web page template at position corresponding with source text, addition is corresponding with source text to be obtained by calibration
Cypher text, generate the second languages webpage.
Above-mentioned text interpretation method, the first interface provided by Content Management System can directly invoke and Content Management system
The corresponding source text in the address of source text in system, then the second interface by being docked with third party's translation system send out source text
It send to third party's translation system, can realize the machine translation process of source text automatically, without manually in multiple browsers
It is toggled in label, reduces During manual operation, improve translation efficiency.Further according to acting on text editing interface,
It is directed to the edit operation of machine translation text, calibration machine cypher text can ensure on the basis of improving translation efficiency
Translation quality.In this way, third party's translation system turn over source text by way of machine translation combines editor's calibration
It translates, it is possible to reduce During manual operation reduces error probability, and calibrated machine translation text to ensure the matter of translation
Amount reduces rework rate, further improves text translation efficiency.
It should be understood that although each step in the flow chart of Fig. 2-5 is shown successively according to the instruction of arrow,
These steps are not that the inevitable sequence indicated according to arrow executes successively.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-5
Part steps may include that either these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can either the sub-step of other steps or at least part in stage be in turn or alternately with other steps
It executes.
In one embodiment, as shown in fig. 6, providing a kind of text translating equipment, including：Acquisition module 601 calls
Module 602, sending module 603, receiving module 604, display module 605 and calibration module 606, wherein：
Acquisition module 601, the address for obtaining source text in Content Management System.
Calling module 602, the first interface for being provided by Content Management System call source document corresponding with address
This.
Sending module 603 sends the source text of calling for the second interface by being docked with third party's translation system
To third party's translation system.
Receiving module 604, for by second interface, receiving the machine corresponding with source text of third party's translation system feedback
Device cypher text.
Display module 605 is used for text exhibition editing interface, and displaying is in editable state in text editing interface
Machine translation text.
Calibration module 606, for according to the edit operation for acting on text editing interface, calibrating the machine translation text of displaying
This.
Above-mentioned text translating equipment, the first interface provided by Content Management System can directly invoke and Content Management system
The corresponding source text in the address of source text in system, then the second interface by being docked with third party's translation system send out source text
It send to third party's translation system, can realize the machine translation process of source text automatically, without manually in multiple browsers
It is toggled in label, reduces During manual operation, improve translation efficiency.Further according to acting on text editing interface,
It is directed to the edit operation of machine translation text, calibration machine cypher text can ensure on the basis of improving translation efficiency
Translation quality.In this way, third party's translation system turn over source text by way of machine translation combines editor's calibration
It translates, it is possible to reduce During manual operation reduces error probability, and calibrated machine translation text to ensure the matter of translation
Amount reduces rework rate, further improves text translation efficiency.
In one embodiment, acquisition module 601 is additionally operable to the first text label of displaying；It detects and chooses the first text mark
When the operation of label, the address included by address range corresponding with the first text label is determined；Address is for positioning Content Management
Source text in system；Displaying is with the second text label that address is link；When detecting the operation for choosing the second text label,
Obtain the address that the second text label chosen is linked.
In above-described embodiment, by detect be directed in the first text label of displaying when choosing operation, determine with
The address included by the corresponding address range of the first text label chosen, displaying is with the second text mark that address above mentioned is link
Label.Thus the address that the second text label chosen is linked can be obtained by choosing the second text label, simplified
It is manually entered the operation of the address of source text, improves the acquisition efficiency of source text.
As shown in fig. 7, in one embodiment, text translating equipment 600 further includes：Separation module 607, input module
608 and correcting module 609.
Separation module 607, for isolating whole sentence from machine cypher text.
Input module 608 obtains the language isolated from whole sentence for whole sentence to be inputted the machine learning model trained
Method element unit.
Correcting module 609, for according to the corresponding default linguistic constraints condition of grammatical feature unit, identifying translation error
Grammatical feature unit is simultaneously corrected, and revised machine translation text is obtained.
In above-described embodiment, by the way that the whole sentence in machine translation text is inputted the machine learning model trained, obtain
The grammatical feature unit isolated from whole sentence identifies the grammatical feature list of translation error further according to default linguistic constraints condition
Member is simultaneously corrected, and can be carried out wrong identification and amendment automatically to machine translation text, be improved text translation efficiency.
In one embodiment, text translating equipment 600 further includes format converting module 610.
Format converting module 610, for be converted into matching with third party's translation system by the file format of source text
File format.
Sending module 603 is additionally operable to the second interface by being docked with third party's translation system, after convert file formats
Source text be sent to third party's translation system.
Format converting module 610 is additionally operable to for the file format of the machine translation text of reception to be converted into the file of source text
Format.
In above-described embodiment, terminal is by the way that the file format of source text to be converted into matching with third party's translation system
File format may be implemented to be docked with third party system automatically, so that third party's translation system can identify that source text is gone forward side by side
Row machine translation.Terminal sends source text by second interface and receives machine cypher text, can in text editing interface with
The file format of source text shows machine cypher text.
In one embodiment, text translating equipment 600 further includes memory module 611.
Acquisition module 601 is additionally operable to obtain cypher text storage address corresponding with address in Content Management System.
Memory module 611 is used for according to cypher text storage address, by what is obtained after the machine translation text of calibration displaying
Cypher text is stored into Content Management System.
In above-described embodiment, terminal can store cypher text to specified translation text corresponding with the address of source text
This storage address can obtain source text and corresponding translation text when that need to use cypher text directly from Content Management System
This, it is convenient and efficient.
As shown in figure 8, in one embodiment, source text is the web page contents in the webpage of the first languages；The text is turned over
It further includes add module 612 to translate device 600.
Acquisition module 601 is additionally operable to obtain the web page template of the webpage of the first languages.
Add module 612, at position corresponding with source text, adding warp corresponding with source text in web page template
The cypher text that calibration obtains is crossed, the webpage of the second languages is generated.
In above-described embodiment, when text interpretation method is applied to multilingual webpage development, source text is the first languages
Web page contents in webpage, terminal can add warp corresponding with source text in web page template at position corresponding with source text
The cypher text that calibration obtains is crossed, the webpage of the second languages is generated.Cypher text to be directly acquired from Content Management System logical in this way
The webpage that cypher text generates the second languages is crossed, the efficiency of multilingual webpage development is improved.
Specific about text translating equipment limits the restriction that may refer to above for text interpretation method, herein not
It repeats again.Modules in above-mentioned text translating equipment can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in or independently of in the processor in computer equipment, can also store in a software form in the form of hardware
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 9.The computer equipment includes the processor connected by system bus, memory, network interface, display
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate by network connection with external terminal.When the computer program is executed by processor with
Realize a kind of text interpretation method.The display screen of the computer equipment can be liquid crystal display or electric ink display screen,
The input unit of the computer equipment can be the touch layer covered on display screen, can also be to be arranged on computer equipment shell
Button, trace ball or Trackpad, can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 9, is only tied with the relevant part of application scheme
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
May include either combining certain components than more or fewer components as shown in the figure or being arranged with different components.
In one embodiment, a kind of computer equipment, including memory and processor are provided, memory is stored with meter
Calculation machine program, processor realize following steps when executing computer program：Obtain the address of source text in Content Management System；It is logical
The first interface for crossing Content Management System offer calls source text corresponding with address；By being docked with third party's translation system
Second interface, the source text of calling is sent to third party's translation system；By second interface, third party's translation system is received
The machine translation text corresponding with source text of feedback；Text exhibition editing interface, and show and be in text editing interface
The machine translation text of editable state；According to the edit operation for acting on text editing interface, the machine translation of displaying is calibrated
Text.
In one embodiment, following steps are also realized when processor executes computer program：Show the first text label；
When detecting the operation for choosing the first text label, the address included by address range corresponding with the first text label is determined；
Address is used to position the source text in Content Management System；Displaying is with the second text label that address is link；It detects and chooses
When the operation of the second text label, the address that the second text label chosen is linked is obtained.
In one embodiment, following steps are also realized when processor executes computer program：From machine cypher text
Isolate whole sentence；Whole sentence is inputted to the machine learning model trained, obtains the grammatical feature unit isolated from whole sentence；It presses
According to the corresponding default linguistic constraints condition of grammatical feature unit, identifies the grammatical feature unit of translation error and correct, repaiied
Machine translation text after just.
In one embodiment, following steps are also realized when processor executes computer program：By the tray of source text
Formula is converted into the file format to match with third party's translation system；By the second interface docked with third party's translation system,
Source text after convert file formats is sent to third party's translation system；By second interface, third party's translation system is received
The machine translation text corresponding with source text of feedback；The file format of the machine translation text of reception is converted into source text
File format.
In one embodiment, following steps are also realized when processor executes computer program：Obtain Content Management System
In cypher text storage address corresponding with address；According to cypher text storage address, by the machine translation text of calibration displaying
The cypher text obtained after this is stored into Content Management System.
In one embodiment, source text is the web page contents in the webpage of the first languages；Processor executes computer journey
Following steps are also realized when sequence：Obtain the web page template of the webpage of the first languages；The position corresponding with source text in web page template
Place is set, the cypher text obtained by calibration corresponding with source text is added, generates the webpage of the second languages.
Above computer equipment, the first interface provided by Content Management System can directly invoke and Content Management System
The corresponding source text in address of middle source text, then the second interface by being docked with third party's translation system send source text
To third party's translation system, the machine translation process of source text can be realized automatically, without manually in multiple browser marks
It is toggled in label, reduces During manual operation, improve translation efficiency.Further according to acting on text editing interface, needle
Edit operation for machine translation text, calibration machine cypher text can have been ensured on the basis of improving translation efficiency and turned over
Translate quality.In this way, third party's translation system translate source text by way of machine translation combines editor's calibration,
During manual operation can be reduced, reduces error probability, and calibrated machine translation text to ensure the quality of translation,
Rework rate is reduced, text translation efficiency is further improved.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor：Obtain the address of source text in Content Management System；Pass through Content Management
The first interface that system provides calls source text corresponding with address；It is connect by docked with third party's translation system second
Mouthful, the source text of calling is sent to third party's translation system；By second interface, receive third party's translation system feedback with
The corresponding machine translation text of source text；Text exhibition editing interface, and displaying is in editable shape in text editing interface
The machine translation text of state；According to the edit operation for acting on text editing interface, the machine translation text of displaying is calibrated.
In one embodiment, following steps are also realized when processor executes computer program：Show the first text label；
When detecting the operation for choosing the first text label, the address included by address range corresponding with the first text label is determined；
Address is used to position the source text in Content Management System；Displaying is with the second text label that address is link；It detects and chooses
When the operation of the second text label, the address that the second text label chosen is linked is obtained.
In one embodiment, following steps are also realized when processor executes computer program：From machine cypher text
Isolate whole sentence；Whole sentence is inputted to the machine learning model trained, obtains the grammatical feature unit isolated from whole sentence；It presses
According to the corresponding default linguistic constraints condition of grammatical feature unit, identifies the grammatical feature unit of translation error and correct, repaiied
Machine translation text after just.
In one embodiment, following steps are also realized when processor executes computer program：By the tray of source text
Formula is converted into the file format to match with third party's translation system；By the second interface docked with third party's translation system,
Source text after convert file formats is sent to third party's translation system；By second interface, third party's translation system is received
The machine translation text corresponding with source text of feedback；The file format of the machine translation text of reception is converted into source text
File format.
In one embodiment, following steps are also realized when processor executes computer program：Obtain Content Management System
In cypher text storage address corresponding with address；According to cypher text storage address, by the machine translation text of calibration displaying
The cypher text obtained after this is stored into Content Management System.
In one embodiment, source text is the web page contents in the webpage of the first languages；Processor executes computer journey
Following steps are also realized when sequence：Obtain the web page template of the webpage of the first languages；The position corresponding with source text in web page template
Place is set, the cypher text obtained by calibration corresponding with source text is added, generates the webpage of the second languages.
Above computer readable storage medium storing program for executing, the first interface provided by Content Management System can directly invoke and content
The corresponding source text in the address of source text in management system, then the second interface by being docked with third party's translation system is by source
Text is sent to third party's translation system, the machine translation process of source text can be realized automatically, without manually multiple
It is toggled in browser label, reduces During manual operation, improve translation efficiency.Further according to acting on text editing circle
Face, it is directed to the edit operation of machine translation text, calibration machine cypher text can be protected on the basis of improving translation efficiency
Translation quality is hindered.In this way, third party's translation system carry out machine translation combine editor calibration by way of to source text into
Row translation, it is possible to reduce During manual operation reduces error probability, and is calibrated to machine translation text to ensure translation
Quality, reduce rework rate, further improve text translation efficiency.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein,
Any reference to memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above example can be combined arbitrarily, to keep description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield is all considered to be the range of this specification record.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the protection domain of the application patent should be determined by the appended claims.
Claims (10)
1. a kind of text interpretation method, the method includes：
Obtain the address of source text in Content Management System；
Source text corresponding with described address is called by the first interface that the Content Management System provides；
By the second interface docked with third party's translation system, the source text of calling is sent to the third party and is translated
System；
By the second interface, machine translation corresponding with the source text text of third party's translation system feedback is received
This；
Text exhibition editing interface, and machine translation text of the displaying in editable state in the text editing interface；
According to the edit operation for acting on the text editing interface, the machine translation text of displaying is calibrated.
2. according to the method described in claim 1, it is characterized in that, it is described obtain Content Management System in source text address,
Including：
Show the first text label；
When detecting the operation for choosing first text label, address range corresponding with first text label institute is determined
Including address；Described address is used to position the source text in the Content Management System；
Displaying is with the second text label that described address is link；
When detecting the operation for choosing second text label, the address that the second text label chosen is linked is obtained.
3. according to the method described in claim 1, it is characterized in that, the text exhibition editing interface, and being compiled in the text
In editing interface before machine translation text of the displaying in editable state, the method further includes：
Whole sentence is isolated from the machine translation text；
The whole sentence is inputted into the machine learning model trained, obtains the grammatical feature unit isolated from the whole sentence；
According to the corresponding default linguistic constraints condition of the grammatical feature unit, identifies the grammatical feature unit of translation error and repair
Just, revised machine translation text is obtained.
4. according to the method described in claim 1, it is characterized in that, second the connecing by being docked with third party's translation system
Mouthful, before the step of source text of calling is sent to third party's translation system, the method further includes：
The file format that the file format of the source text is converted into matching with third party's translation system；
The source text of calling is sent to the third party by the second interface by being docked with third party's translation system
Translation system includes：
By the second interface docked with third party's translation system, the source text after convert file formats is sent to the third
Square translation system；
It is described by the second interface, the machine corresponding with the source text for receiving third party's translation system feedback turns over
After this step of of translation, the method further includes：
The file format of the machine translation text of reception is converted into the file format of the source text.
5. according to the method described in claim 1, it is characterized in that, the method further includes：
Obtain cypher text storage address corresponding with described address in the Content Management System；
According to the cypher text storage address, the cypher text obtained after the machine translation text for calibrating the displaying is stored
To in the Content Management System.
6. method according to any one of claims 1 to 5, which is characterized in that the source text is the webpage of the first languages
In web page contents；The method further includes：
Obtain the web page template of the webpage of first languages；
In the web page template at position corresponding with the source text, add corresponding with the source text by calibrating
The cypher text arrived generates the webpage of the second languages.
7. a kind of text translating equipment, which is characterized in that described device includes：
Acquisition module, the address for obtaining source text in Content Management System；
Calling module, the first interface for being provided by the Content Management System call source document corresponding with described address
This；
The source text of calling is sent to by sending module for the second interface by being docked with third party's translation system
Third party's translation system；
Receiving module is feeding back with the source text phase for by the second interface, receiving third party's translation system
The machine translation text answered；
Display module is used for text exhibition editing interface, and displaying is in editable state in the text editing interface
Machine translation text；
Calibration module, for according to the edit operation for acting on the text editing interface, calibrating the machine translation text of displaying.
8. device according to claim 7, which is characterized in that described device further includes：
Separation module, for isolating whole sentence from the machine translation text；
Input module obtains isolating from the whole sentence for the whole sentence to be inputted the machine learning model trained
Grammatical feature unit；
Correcting module, for according to the corresponding default linguistic constraints condition of the grammatical feature unit, identifying the language of translation error
Method element unit is simultaneously corrected, and revised machine translation text is obtained.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In when the processor executes the computer program the step of any one of realization claim 1 to 6 the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method according to any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810124553.6A CN108399166B (en) | 2018-02-07 | 2018-02-07 | Text translation method and device, computer equipment and storage medium |
| PCT/CN2019/070018 WO2019153979A1 (en) | 2018-02-07 | 2019-01-02 | Text translation method, apparatus, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810124553.6A CN108399166B (en) | 2018-02-07 | 2018-02-07 | Text translation method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108399166A true CN108399166A (en) | 2018-08-14 |
| CN108399166B CN108399166B (en) | 2021-03-30 |
Family
ID=63095431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810124553.6A Active CN108399166B (en) | 2018-02-07 | 2018-02-07 | Text translation method and device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108399166B (en) |
| WO (1) | WO2019153979A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110047488A (en) * | 2019-03-01 | 2019-07-23 | 北京彩云环太平洋科技有限公司 | Voice translation method, device, equipment and control equipment |
| WO2019153979A1 (en) * | 2018-02-07 | 2019-08-15 | 深圳壹账通智能科技有限公司 | Text translation method, apparatus, computer device and storage medium |
| CN110134586A (en) * | 2019-04-12 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Code snippet correcting method, device, computer equipment and storage medium |
| CN111428523A (en) * | 2020-03-23 | 2020-07-17 | 腾讯科技（深圳）有限公司 | Translation corpus generation method and device, computer equipment and storage medium |
| CN111857906A (en) * | 2020-06-03 | 2020-10-30 | 北京旷视科技有限公司 | Text display method, device and system of terminal and storage medium |
| CN114091483A (en) * | 2021-10-27 | 2022-02-25 | 北京百度网讯科技有限公司 | Translation processing method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101086731A (en) * | 2006-06-05 | 2007-12-12 | 李钢 | Multi-country instant online translation system based on server |
| WO2010105383A1 (en) * | 2009-03-18 | 2010-09-23 | Google Inc. | Web translation with display replacement |
| US7974832B2 (en) * | 2007-12-12 | 2011-07-05 | Microsoft Corporation | Web translation provider |
| CN105573969A (en) * | 2006-10-02 | 2016-05-11 | 谷歌公司 | Displaying original text in a user interface with translated text |
| CN106557467A (en) * | 2015-09-28 | 2017-04-05 | 四川省科技交流中心 | Machine translation system and interpretation method based on bridge language |
| CN107301176A (en) * | 2017-06-30 | 2017-10-27 | 广东欧珀移动通信有限公司 | A kind of interpretation method, device and storage medium, electronic equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2004202391A1 (en) * | 2003-06-20 | 2005-01-13 | Microsoft Corporation | Adaptive machine translation |
| CN102193912B (en) * | 2010-03-12 | 2013-11-06 | 富士通株式会社 | Phrase division model establishing method, statistical machine translation method and decoder |
| CN104391839A (en) * | 2014-11-13 | 2015-03-04 | 百度在线网络技术（北京）有限公司 | Method and device for machine translation |
| CN106326213A (en) * | 2015-06-19 | 2017-01-11 | 北京京东尚科信息技术有限公司 | Method and device for translating WEB site |
| CN105912534A (en) * | 2016-05-09 | 2016-08-31 | 珠海市魅族科技有限公司 | Translation method and device |
| CN108399166B (en) * | 2018-02-07 | 2021-03-30 | 深圳壹账通智能科技有限公司 | Text translation method and device, computer equipment and storage medium |
-
2018
- 2018-02-07 CN CN201810124553.6A patent/CN108399166B/en active Active
-
2019
- 2019-01-02 WO PCT/CN2019/070018 patent/WO2019153979A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101086731A (en) * | 2006-06-05 | 2007-12-12 | 李钢 | Multi-country instant online translation system based on server |
| CN105573969A (en) * | 2006-10-02 | 2016-05-11 | 谷歌公司 | Displaying original text in a user interface with translated text |
| US7974832B2 (en) * | 2007-12-12 | 2011-07-05 | Microsoft Corporation | Web translation provider |
| WO2010105383A1 (en) * | 2009-03-18 | 2010-09-23 | Google Inc. | Web translation with display replacement |
| CN106557467A (en) * | 2015-09-28 | 2017-04-05 | 四川省科技交流中心 | Machine translation system and interpretation method based on bridge language |
| CN107301176A (en) * | 2017-06-30 | 2017-10-27 | 广东欧珀移动通信有限公司 | A kind of interpretation method, device and storage medium, electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 刘里: "《基于术语长度和语法特征的统计领域术语抽取》", 《哈尔滨工程大学学报》 * |
| 王广义: "《机器翻译系统文法中语法和语义研究—《天语》英汉翻译系统的文法概要》", 《中文信息学报》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019153979A1 (en) * | 2018-02-07 | 2019-08-15 | 深圳壹账通智能科技有限公司 | Text translation method, apparatus, computer device and storage medium |
| CN110047488A (en) * | 2019-03-01 | 2019-07-23 | 北京彩云环太平洋科技有限公司 | Voice translation method, device, equipment and control equipment |
| CN110047488B (en) * | 2019-03-01 | 2022-04-12 | 北京彩云环太平洋科技有限公司 | Voice translation method, device, equipment and control equipment |
| CN110134586A (en) * | 2019-04-12 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Code snippet correcting method, device, computer equipment and storage medium |
| WO2020206839A1 (en) * | 2019-04-12 | 2020-10-15 | 深圳壹账通智能科技有限公司 | Code snippet correction method and apparatus, computer device, and storage medium |
| CN111428523A (en) * | 2020-03-23 | 2020-07-17 | 腾讯科技（深圳）有限公司 | Translation corpus generation method and device, computer equipment and storage medium |
| CN111428523B (en) * | 2020-03-23 | 2023-09-01 | 腾讯科技（深圳）有限公司 | Translation corpus generation method, device, computer equipment and storage medium |
| CN111857906A (en) * | 2020-06-03 | 2020-10-30 | 北京旷视科技有限公司 | Text display method, device and system of terminal and storage medium |
| CN111857906B (en) * | 2020-06-03 | 2022-02-01 | 北京旷视科技有限公司 | Text display method, device and system of terminal and storage medium |
| CN114091483A (en) * | 2021-10-27 | 2022-02-25 | 北京百度网讯科技有限公司 | Translation processing method and device, electronic equipment and storage medium |
| CN114091483B (en) * | 2021-10-27 | 2023-02-28 | 北京百度网讯科技有限公司 | Translation processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019153979A1 (en) | 2019-08-15 |
| CN108399166B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108399166A (en) | Text interpretation method, device, computer equipment and storage medium | |
| CN107908635B (en) | Method and device for establishing text classification model and text classification | |
| KR101279759B1 (en) | Web-based collocation error proofing | |
| CN100452023C (en) | System and method for providing a transient dictionary that travels with an original electronic document | |
| US20140298167A1 (en) | Electronic book pagination | |
| CN102317936A (en) | Identifying comments to show in connection with a document | |
| US9213690B2 (en) | Method, system, and appartus for selecting an acronym expansion | |
| CN111176996A (en) | Test case generation method and device, computer equipment and storage medium | |
| CN110955608B (en) | Test data processing method, device, computer equipment and storage medium | |
| WO2019224891A1 (en) | Classification device, classification method, generation method, classification program, and generation program | |
| CN106030568A (en) | Natural language processing system, natural language processing method, and natural language processing program | |
| US20150205765A1 (en) | Font process method and font process system | |
| CN110362476A (en) | Verification method, device, computer equipment and the storage medium of data conversion tools | |
| Huo et al. | ARCLIN: automated API mention resolution for unformatted texts | |
| CN117010345A (en) | Method, device, equipment and storage medium for generating function document | |
| Kuncham et al. | Statistical sandhi splitter for agglutinative languages | |
| US10755047B2 (en) | Automatic application of reviewer feedback in data files | |
| US20220121881A1 (en) | Systems and methods for enabling relevant data to be extracted from a plurality of documents | |
| US8219903B2 (en) | Display information verification program, method and apparatus | |
| CN114491209A (en) | Method and system for mining enterprise business label based on internet information capture | |
| CN111581950B (en) | Method for determining synonym names and method for establishing knowledge base of synonym names | |
| CN115687075A (en) | Error correction method and device for page test script | |
| US11288451B2 (en) | Machine based expansion of contractions in text in digital media | |
| US11966421B2 (en) | System, method, and computer program for a context-based data-driven classifier | |
| Feng et al. | Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |