CN104933041A - File extraction and reduction method favorable for translation work - Google Patents
File extraction and reduction method favorable for translation work Download PDFInfo
- Publication number
- CN104933041A CN104933041A CN201510357672.2A CN201510357672A CN104933041A CN 104933041 A CN104933041 A CN 104933041A CN 201510357672 A CN201510357672 A CN 201510357672A CN 104933041 A CN104933041 A CN 104933041A
- Authority
- CN
- China
- Prior art keywords
- translation
- sentence
- interpreter
- document
- translated
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to an artificial intelligence file processing method favorable for translation work. The method comprises the following steps: utilizing an Aspose assembly to support a file processing operation, and disassembling a file object to be translated into a set of data to be translated, wherein the set of the data to be translated takes a simple sentence as a minimum unit; establishing a standard interpreter processing document, copying each sentence in the set of data to be translated to the interpreter processing document one by one; filling translations in the interpreter processing document by an interpreter one by one; traversing the set of data to be translated and the interpreter processing document, and writing the translations into the set of data to be translated; and reducing the set of data to be translated to an original manuscript format document. Various manuscripts of different formats can be converted into the standard interpreter processing document. Sentences which repeatedly appear for multiple times do not need to be repeatedly translated for multiple times, the translation work of the interpreter is simplified, translation efficiency is improved, the execution efficiencies of extraction logics and reduction logics are high, and a reduced translation manuscript reserves an original manuscript format.
Description
Technical field
The present invention relates to and be a kind ofly beneficial to the artificial intelligence of translation, the method for document process.
Background technology
Rank among second-biggest-in-the-world economy along with China, the steady enforcement of strategies such as " one band one tunnel ", contacting of Chinese each field and the world is more tight.Language Service supportive market required for communication exchange between multinational in international process seems more voluminous, and this brings new opportunities and challenges to translation industry.
The practitioner of translation industry every day will in the face of the contribution of the needs translation of a large amount of various forms, of a great variety due to contribution, corresponding translator just needs to be grasped all kinds of documentor as Word, Excel, the use of PPT, PDF and the use of all kinds of document assisted translation tools.This for sole duty translator be very large challenge and threshold, and even clearly this kind of problem hindered to whole industry development China globalization process.
Therefore, need to propose a kind of by etc. multiple main flow document format be converted into the document of unified standard pattern and also can will transform the standard document that obtains and be reduced to the method for original copy form conversely.To simplify translation, to improve translation efficiency.
Summary of the invention
Technical matters to be solved by this invention simplifies translation, raising translation efficiency, proposes a kind of file being beneficial to translation and extract and method of reducing.
For solving the problems of the technologies described above, the file being beneficial to translation of the present invention's proposition extracts and method of reducing, comprises the following steps:
1) utilize Aspose dynamic link library to the operation support of document process, disassembling into document object to be translated with simple sentence is the set data to be translated of least unit;
2) set up an interpreter and process document, described interpreter processes document and is provided with " original text ", " translation " and id tri-fields, the corresponding sentence original text of described " original text " field, the corresponding sentence translation of " translation " field;
3) each sentence in the described set data to be translated taking simple sentence as least unit is copied to " original text " field that described interpreter processes document in order one by one, then the content of this sentence in the set data to be translated occupy-place symbol Guid that has uniqueness is substituted, and adjacent occupy-place symbol Guid has different character format; The content of described id field has between described different Guid the relation mapped one by one;
4) described interpreter is processed document and be issued to interpreter, described interpreter processes the original text translating " original text " field in document one by one described interpreter, is filled up to corresponding " translation " field, until processed;
5) travel through described set data to be translated and interpreter processes document, the different ids corresponding according to different Guid, find the translation that this id is corresponding, cover the position of writing this corresponding Guid in described set data to be translated.
6) call Aspose dynamic link library, described set data to be translated is reduced to the document of original copy form.
Described disassemble into document object to be translated with sentence is the set data to be translated of least unit, comprises the following steps:
1-1 calls Aspose assembly;
1-2 travels through described document object, obtains whole paragraph object, and described paragraph object comprises the whole Word message of document object, and does not comprise symbol, image or other the non-legible information without the need to translating;
1-3 travels through the child node object of each paragraph object, thus obtains several character set object Run.There is provided paragraph object, child node object in Aspose assembly, and facilitate the Run object of character manipulation, described Run is to liking the character fragments set that in document, continuous print character format is consistent.
1-4 travels through each Run object, whole Run object is split into the Run object only including a complete sentence one by one, or for only including the Run object of a sentence fragment;
1-5 travels through each Run object, follow-up only to be included in the Run object of a complete sentence by the Run object merging only including sentence fragment to it.
After completing, obtaining take sentence as least unit, only to include the set of the Run object of a complete sentence one by one.
Describedly will only include the Run object merging of a sentence fragment to follow-up Run object, comprise the following steps:
The character content that 1-4-1 will only be the Run object of a sentence fragment is taken out, and leaves temporary storage cell in, then in paragraph object, deletes this Run object;
1-4-2 checks next Run object, if the character content of this Run object is only a sentence fragment, then takes out the character content of this Run object, add temporary storage cell to, then in paragraph object, delete this Run object, continue to check next but one Run object; Otherwise, take out temporary storage cell and deposit character content, before adding the character content of this next Run object to, then empty described temporary storage cell.
If the character content of this next Run object of 1-4-3 is using sentence end mark as ending, the character content then deposited by described temporary storage cell is taken out, before adding the character content of this next Run object to, then empty described temporary storage cell.
The present invention also comprises, and sets up a dictionary object, and the key of described dictionary object is original text, and value is translation, and original text-translation is a key-value pair; When traveling through described interpreter and processing document, original text-translation corresponding in recording, writes described dictionary object respectively.
In step 5) in, if the translation hurdle of an id place record is empty, then in described dictionary object, with the original text of this id place record for key removes to search the translation value whether having coupling, if found, fill translation hurdle with this translation.
If in described dictionary object, do not find the translation value of coupling, then this sentence is that leakage is translated, and directly uses original text to fill, and the personnel that conveniently examine and revise find.
Further, described interpreter being processed before document is issued to interpreter, traveling through described interpreter and processing document, the sentence of repetition is marked, reminding interpreter not need to repeat translation.
Further, described interpreter being processed before document is issued to interpreter, traveling through described interpreter and processing document, sentence in original text and the term in terminology bank are carried out Auto-matching, if coupling, then annotate and comment on this term sentence, make translation more smooth and easy.
Further, described interpreter being processed before document is issued to interpreter, traveling through described interpreter and processing document, the sentence in original text is mated with the language material comparison in corpus one by one, if coupling, be then filled up to the language material translation in corpus in " translation " field corresponding to this coupling sentence.
Beneficial effect: the present invention simplifies the work of translator, makes translator without the need to grasping the use disposal route of all kinds of main flow documentor as PPT, Word, EXCL, PDF, thus more energy can be had to be absorbed in the work of character translation go.In addition, by the manuscript translated needed for preanalysis automatic in processing procedure, the sentence searching out repeatability marks, and the sentence of all repeatability all only needs translation once, other then automatic filling generations; Collect each translation achievement, the information such as the language material accumulating out before can directly using when receiving new contribution and term, further improve translation efficiency.
Accompanying drawing explanation
Below in conjunction with the drawings and specific embodiments, technical scheme of the present invention is further described in detail.
Fig. 1 is that the interpreter of the specific embodiment of the invention translates process interface sectional drawing, and the interpreter having filled original text of the main presentation in figure processes document.
Fig. 2 is that another interpreter of the specific embodiment of the invention translates process interface sectional drawing, and the main presentation in figure one processes document through pretreated interpreter.
Fig. 3 is overall flow figure of the present invention.
Embodiment
The file being beneficial to translation of the present invention's proposition extracts and method of reducing, comprises the following steps:
1) utilize Aspose dynamic link library to the operation support of document process, disassembling into document object to be translated with simple sentence is the set data to be translated of least unit;
2) set up an interpreter and process document, described interpreter processes document and is provided with " original text ", " translation " and id tri-fields, the corresponding sentence original text of described " original text " field, the corresponding sentence translation of " translation " field;
3) each sentence in the described set data to be translated taking simple sentence as least unit is copied to " original text " field that described interpreter processes document in order one by one, then the content of this sentence in the set data to be translated occupy-place symbol Guid that has uniqueness is substituted, and adjacent occupy-place symbol Guid has different character format; The content of described id field has between described different Guid the relation mapped one by one;
4) described interpreter is processed document and be issued to interpreter, described interpreter processes the original text translating " original text " field in document one by one described interpreter, is filled up to corresponding " translation " field, until processed;
5) travel through described set data to be translated and interpreter processes document, the different ids corresponding according to different Guid, find the translation that this id is corresponding, cover the position of writing this corresponding Guid in described set data to be translated.
6) call Aspose dynamic link library, described set reduction data to be translated is generated the translation manuscript that document processing tools identifies.
For more understanding the present invention, below with the process of Word document, be translated as example, describe translation processing procedure of the present invention in detail:
S1, call Aspose assembly;
S2, travel through Word document object to be translated, obtain whole paragraph object, this paragraph object comprises the whole Word message of document object, and does not comprise without the need to the symbol of translation, image or other non-legible information;
S3, travel through the child node object of each paragraph object, thus obtain several character set object Run;
Aspose assembly provides paragraph object, child node object, and facilitates the Run object of character manipulation; Run is to liking the character set that in document, continuous print character format is consistent.
There are 4 kinds of situations in the Run object obtained: 1. a Run object includes multiple complete sentence; 2. a Run object includes multiple complete sentence and some sentence fragments; 3. a Run object only comprises a sentence fragment; 4. Run object comprises a complete sentence.Therefore, need process of further making pauses in reading unpunctuated ancient writings, existing Run object is split and merged, obtain only including one by one the Run object of a complete sentence.
S4, fractionation: travel through each Run object, split into the Run object only including a complete sentence one by one by whole Run object, or for only including the Run object of a sentence fragment.The mode adopted is such as:
From first described Run object, check the character content of this Run object,
If Run object only includes a complete sentence, or a sentence fragment, then directly check next Run object;
If a Run object includes multiple complete sentence, then by this Run object with sentence end mark for boundary, split into several Run object only comprising a complete words.
If a Run object includes multiple complete sentence and a sentence fragment, then by this Run object with sentence end mark for boundary, split into several Run object only comprising a complete words, and a Run object comprising a sentence fragment.
Such as, passage for " in order to solve the problem, special propose a kind of by Word, Excel; the multiple main flow such as PPT, PDF document format is converted into the Word document of unified standard pattern and also can will transforms the standard Word document obtained and be reduced to the method for original copy form conversely.To simplify translation, to improve translation efficiency.”
To above-mentioned passage, application Aspose assembly, after traveling through above-mentioned paragraph object, obtain several character set object Run, order is respectively: Run-1: " in order to solve the problem; special propose a kind of will ", Run-2: " Word; Excel; PPT, PDF ", Run-3: " wait multiple main flow document format be converted into unified standard pattern ", Run-4: " Word ", Run-5: " document and also can will transform the standard obtained conversely ", Run-6: " Word ", Run-7: " document is reduced to the method for original copy form.To simplify translation, to improve translation efficiency.”
Obviously, above-mentioned Run-1 to Run-6, just comprises a sentence fragment, and Run-7 comprises two sentences seeming complete.Generate the data acquisition in units of complete words, Run-1 to Run-6 needs to merge, and Run-7 needs to split further.
S5, merging: travel through each Run object, follow-up only to include the Run object merging only including sentence fragment in the Run object of a complete sentence to it.Specifically comprise the following steps:
The character content that S5-1 will only be the Run object of a sentence fragment is taken out, and leaves temporary storage cell in, then in paragraph object, deletes this Run object;
S5-2 checks next Run object, if the character content of this Run object is only a sentence fragment, then takes out the character content of this Run object, add temporary storage cell to, then in paragraph object, delete this Run object, continue to check next but one Run object; Otherwise, take out temporary storage cell and deposit character content, before adding the character content of this next Run object to, then empty temporary storage cell.
If the character content of this next Run object of S5-3 is using sentence end mark as ending, then the character content deposited by described temporary storage cell is taken out, and before adding the character content of this next Run object to, then empties described temporary storage cell.
After completing, obtaining take sentence as least unit, only to include the set of the Run object of a complete sentence one by one.
S6, set up an interpreter and process document, interpreter processes document and is provided with " original text ", " translation " and id tri-fields, the corresponding sentence original text of " original text " field, the corresponding sentence translation of " translation " field;
S7, by with simple sentence be least unit set data to be translated in each sentence copy to " original text " field that described interpreter processes document in order one by one, then the content of this sentence in the set data to be translated occupy-place symbol Guid that has uniqueness is substituted, and adjacent occupy-place symbol Guid has different character format, such as, give adjacent occupy-place symbol Guid with different colors, make the character format of adjacent Guid different; There is between the content of id field and different Guid the relation mapped one by one;
S8, travel through described interpreter and process document, the sentence of repetition is marked.As shown in Figure 2, " Android integration guide " repeats, then mark with colour band, reminds interpreter not need to repeat translation.
S9, travel through described interpreter and process document, the sentence in original text and the term in terminology bank are carried out Auto-matching, if coupling, then this term sentence is annotated and commented on, make translation more smooth and easy.
S10, travel through described interpreter and process document, the sentence in original text is mated with the language material comparison in corpus one by one, if 100% coupling, then the language material translation in corpus is filled up in " translation " field corresponding to this coupling sentence.As in Fig. 2, there is conventional corresponding translation " SDKdownload " in " SDK download " in language material, and " FAQs " exists conventional corresponding translation " FAQ " in language material.Language material translation in corpus is filled up in " translation " field corresponding to this coupling sentence.If when matching degree is less than 100%, this guild is marked as certain color.This sentence is indicated to need interpreter to translate, but first automatic filling language material translation, for interpreter with reference to, amendment.
S11, interpreter is processed document be issued to interpreter, interpreter processes the original text translating " original text " field in document one by one described interpreter, be filled up to corresponding " translation " field, until processed;
S12, set up a dictionary object, the key of described dictionary object is original text, and value is translation, and original text-translation is a key-value pair; When traveling through described interpreter and processing document, original text-translation corresponding in recording, writes described dictionary object respectively.
S13, being uploaded onto the server as new language material to information by this language material remains, in next translation, and reference.
S14, travel through described set data to be translated and interpreter processes document, the different ids corresponding according to different Guid, find the translation that this id is corresponding, cover the position of writing this corresponding Guid in described set data to be translated.
If the translation hurdle of an id place record is empty, then in dictionary object, with the original text of this id place record for key removes to search the translation value whether having coupling, if found, fill translation hurdle with this translation.
If in dictionary object, do not find the translation value of coupling, then this sentence is that leakage is translated, and directly uses original text to fill, and the personnel that conveniently examine and revise find.
S15, call Aspose dynamic link library, described set data to be translated is reduced into original copy formatted file.
For EXCL, PPT, PDF document that the present invention mentions, those skilled in the art are by reading herein, can by ASpose assembly, realize the character information that these documents comprise, and according to disclosed method, carry out the fractionation of the data acquisition in units of sentence, combined treatment, generate interpreter and process document, be convenient to interpreter's translation; And after interpreter's translation, the reduction treatment of translation manuscript.Such as, for EXCL, PDF, PPT document, after can first utilizing existing instrument to convert corresponding Word document to, utilizing the method process of above-described embodiment.For EXCL document, also can directly by the process of ASpose assembly.
Obviously, the present invention has following beneficial features:
(1) the method is used the manuscript of multiple different-format can be converted into the standardization document of uniform format.Help the standardized management of translation, thus the translation simplifying interpreter improves translation efficiency.
(2) by the confluence analysis with batch all documents, the sentence repeated is found out.Repeat sentence repeatedly without the need to translation repeatedly, only need to translate when first time occurs, the translation of other these sentences of position will be filled automatically.
(3) the new language material information produced in translation process is saved to cloud service.By the continuous accumulation to language material, promote the translation ability of translator itself gradually.By the means that language material is multiplexing, promote translation efficiency.
(4) standard needing the contribution of translation to be all converted to consolidation form can be treated the manuscript of a translation, facilitate the management of team's translation, reduce the work difficulty of translation project manager.
(5) execution efficiency of extraction and reduction logic is higher, does not substantially bring negative effect to translation.
(6) algorithm can be revised as the case may be during reduction, reach the final effect that form retains.
It should be noted last that, above embodiment is only in order to illustrate technical scheme of the present invention and unrestricted, although with reference to preferred embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that, can modify to technical scheme of the present invention or equivalent replacement, and not departing from the spirit and scope of technical solution of the present invention, it all should be encompassed in the middle of right of the present invention.
Claims (8)
1. the file being beneficial to translation extracts and a method of reducing, it is characterized in that, comprises the following steps:
1) utilize Aspose dynamic link library to the operation support of document process, disassembling into document object to be translated with simple sentence is the set data to be translated of least unit;
2) set up an interpreter and process document, described interpreter processes document and is provided with " original text ", " translation " and id tri-fields, the corresponding sentence original text of described " original text " field, the corresponding sentence translation of " translation " field;
3) each sentence in the described set data to be translated taking simple sentence as least unit is copied to " original text " field that described interpreter processes document in order one by one, then the content of this sentence in the set data to be translated occupy-place symbol Guid that has uniqueness is substituted, and adjacent occupy-place symbol Guid has different character format; The content of described id field has between described different Guid the relation mapped one by one;
4) described interpreter is processed document and be issued to interpreter, described interpreter processes the original text translating " original text " field in document one by one described interpreter, is filled up to corresponding " translation " field, until processed;
5) travel through described set data to be translated and interpreter processes document, the different ids corresponding according to different Guid, find the translation that this id is corresponding, cover the position of writing this corresponding Guid in described set data to be translated;
6) call Aspose dynamic link library, described set reduction data to be translated is generated original copy format file.
2. the file being beneficial to translation according to claim 1 extracts and method of reducing, it is characterized in that, described disassemble into document object to be translated with sentence is the set data to be translated of least unit, comprises the following steps:
1-1 calls Aspose assembly;
1-2 travels through described document object, obtains whole paragraph object, and described paragraph object comprises the whole Word message of document object, and does not comprise symbol, image or other the non-legible information without the need to translating;
1-3 travels through the child node object of each paragraph object, thus obtains several character set object Run;
1-4 travels through each Run object, whole Run object is split into the Run object only including a complete sentence one by one, or for only including the Run object of a sentence fragment;
1-5 travels through each Run object, follow-up only to be included in the Run object of a complete sentence by the Run object merging only including sentence fragment to it.
3. the file being beneficial to translation according to claim 2 extracts and method of reducing, it is characterized in that, describedly will only include the Run object merging of a sentence fragment to follow-up Run object, comprises the following steps:
The character content that 1-4-1 will only be the Run object of a sentence fragment is taken out, and leaves temporary storage cell in, then in paragraph object, deletes this Run object;
1-4-2 checks next Run object, if the character content of this Run object is only a sentence fragment, then takes out the character content of this Run object, add temporary storage cell to, then in paragraph object, delete this Run object, continue to check next but one Run object; Otherwise, take out temporary storage cell and deposit character content, before adding the character content of this next Run object to, then empty described temporary storage cell;
If the character content of this next Run object of 1-4-3 is using sentence end mark as ending, the character content then deposited by described temporary storage cell is taken out, before adding the character content of this next Run object to, then empty described temporary storage cell.
4. the file being beneficial to translation according to claim 1 extracts and method of reducing, and it is characterized in that, also comprise, set up a dictionary object, the key of described dictionary object is original text, and value is translation, and original text-translation is a key-value pair; When traveling through described interpreter and processing document, original text-translation corresponding in recording, writes described dictionary object respectively.
5. the file being beneficial to translation according to claim 4 extracts and method of reducing, it is characterized in that, in step 5) in, if the translation hurdle of an id place record is empty, then in described dictionary object, with the original text of this id place record for key removes to search the translation value whether having coupling, if found, fill translation hurdle with this translation;
If in described dictionary object, do not find the translation value of coupling, then this sentence is that leakage is translated, and directly uses original text to fill.
6. the file being beneficial to translation according to claim 1 extracts and method of reducing, it is characterized in that, described interpreter being processed before document is issued to interpreter, traveling through described interpreter and processing document, the sentence of repetition is marked, reminds interpreter not need to repeat translation.
7. the file being beneficial to translation according to claim 1 extracts and method of reducing, it is characterized in that, described interpreter is being processed before document is issued to interpreter, travel through described interpreter and process document, sentence in original text and the term in terminology bank are carried out Auto-matching, if coupling, then annotate and comment on this term sentence, make translation more smooth and easy.
8. the file being beneficial to translation according to claim 1 extracts and method of reducing, it is characterized in that, described interpreter is being processed before document is issued to interpreter, travel through described interpreter and process document, sentence in original text is mated with the language material comparison in corpus one by one, if coupling, be then filled up to the language material translation in corpus in " translation " field corresponding to this coupling sentence.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510357672.2A CN104933041B (en) | 2015-06-25 | 2015-06-25 | A kind of file beneficial to translation is extracted and restoring method |
| PCT/CN2015/098668 WO2016206336A1 (en) | 2015-06-25 | 2015-12-24 | File extraction and restoration method favorable for translation work |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510357672.2A CN104933041B (en) | 2015-06-25 | 2015-06-25 | A kind of file beneficial to translation is extracted and restoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104933041A true CN104933041A (en) | 2015-09-23 |
| CN104933041B CN104933041B (en) | 2017-09-01 |
Family
ID=54120210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510357672.2A Active CN104933041B (en) | 2015-06-25 | 2015-06-25 | A kind of file beneficial to translation is extracted and restoring method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104933041B (en) |
| WO (1) | WO2016206336A1 (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105677643A (en) * | 2016-03-14 | 2016-06-15 | 张广睿 | Translation method combining manpower and machine |
| CN105760368A (en) * | 2016-03-11 | 2016-07-13 | 张广睿 | Deep processing method for characters of document |
| CN105808528A (en) * | 2016-03-04 | 2016-07-27 | 张广睿 | Document character processing method |
| CN105975451A (en) * | 2016-05-27 | 2016-09-28 | 成都优译信息技术有限公司 | Processing system and method for DWG-format-file translation data |
| CN105975461A (en) * | 2016-05-27 | 2016-09-28 | 成都优译信息技术有限公司 | Method for newly adding translation in DWG format file |
| CN106021242A (en) * | 2016-05-27 | 2016-10-12 | 成都优译信息技术有限公司 | Write-back system of drawing interpretation data in DWG format and write-back method thereof |
| CN106021197A (en) * | 2016-05-27 | 2016-10-12 | 成都优译信息技术有限公司 | Translation system of DWG-format files and translation method |
| CN106055529A (en) * | 2016-05-27 | 2016-10-26 | 成都优译信息技术有限公司 | Analytic system of text data to be translated in DWG-format files and analytic method thereof |
| WO2016206336A1 (en) * | 2015-06-25 | 2016-12-29 | 武汉传神信息技术有限公司 | File extraction and restoration method favorable for translation work |
| CN106919558A (en) * | 2015-12-24 | 2017-07-04 | 姚珍强 | For the interpretation method and translating equipment based on natural dialogue mode of mobile device |
| CN107590140A (en) * | 2017-10-17 | 2018-01-16 | 语联网（武汉）信息技术有限公司 | Entry process method is translated in a kind of document leakage |
| CN107885735A (en) * | 2017-11-21 | 2018-04-06 | 语联网（武汉）信息技术有限公司 | A kind of unrelated document translation method and system of form |
| CN108563645A (en) * | 2018-04-24 | 2018-09-21 | 成都智信电子技术有限公司 | The metadata interpretation method and device of HIS systems |
| CN109446531A (en) * | 2018-09-06 | 2019-03-08 | 语联网（武汉）信息技术有限公司 | Detect the method, apparatus and electronic equipment of translation progress |
| CN109783826A (en) * | 2019-01-15 | 2019-05-21 | 四川译讯信息科技有限公司 | A kind of document automatic translating method |
| CN111144070A (en) * | 2019-12-31 | 2020-05-12 | 北京迈迪培尔信息技术有限公司 | Document parsing translation method and device |
| CN111143074A (en) * | 2019-12-30 | 2020-05-12 | 文思海辉智科科技有限公司 | Method and device for distributing translation files |
| CN111291575A (en) * | 2020-02-28 | 2020-06-16 | 北京字节跳动网络技术有限公司 | Text processing method and device, electronic equipment and storage medium |
| CN112052648A (en) * | 2020-09-02 | 2020-12-08 | 文思海辉智科科技有限公司 | String translation method and device, electronic equipment and storage medium |
| CN112766003A (en) * | 2021-01-20 | 2021-05-07 | 语联网（武汉）信息技术有限公司 | Document auxiliary translation method and device |
| CN113705158A (en) * | 2021-09-26 | 2021-11-26 | 上海一者信息科技有限公司 | Method for intelligently restoring original text style in document translation |
| CN114065782A (en) * | 2021-11-08 | 2022-02-18 | 语联网（武汉）信息技术有限公司 | Method for translating word document and keeping original style |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555196B (en) * | 2018-05-30 | 2023-07-18 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for automatically generating article |
| CN109617974B (en) * | 2018-12-21 | 2021-12-28 | 珠海金山办公软件有限公司 | Request processing method and device and server |
| CN110688863B (en) * | 2019-09-25 | 2023-04-07 | 六维联合信息科技(北京)有限公司 | Document translation system and document translation method |
| CN114638241B (en) * | 2022-03-30 | 2024-10-01 | 阿里巴巴（中国）有限公司 | Data matching method, device, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5848386A (en) * | 1996-05-28 | 1998-12-08 | Ricoh Company, Ltd. | Method and system for translating documents using different translation resources for different portions of the documents |
| CN104331399A (en) * | 2014-07-25 | 2015-02-04 | 一朵云（北京）科技有限公司 | Dictionary tree translation method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982027A (en) * | 2011-09-02 | 2013-03-20 | 北大方正集团有限公司 | Method and device for abstracting contents in document |
| CN104933041B (en) * | 2015-06-25 | 2017-09-01 | 武汉传神信息技术有限公司 | A kind of file beneficial to translation is extracted and restoring method |
-
2015
- 2015-06-25 CN CN201510357672.2A patent/CN104933041B/en active Active
- 2015-12-24 WO PCT/CN2015/098668 patent/WO2016206336A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5848386A (en) * | 1996-05-28 | 1998-12-08 | Ricoh Company, Ltd. | Method and system for translating documents using different translation resources for different portions of the documents |
| CN104331399A (en) * | 2014-07-25 | 2015-02-04 | 一朵云（北京）科技有限公司 | Dictionary tree translation method |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016206336A1 (en) * | 2015-06-25 | 2016-12-29 | 武汉传神信息技术有限公司 | File extraction and restoration method favorable for translation work |
| CN106919558A (en) * | 2015-12-24 | 2017-07-04 | 姚珍强 | For the interpretation method and translating equipment based on natural dialogue mode of mobile device |
| CN105808528A (en) * | 2016-03-04 | 2016-07-27 | 张广睿 | Document character processing method |
| CN105808528B (en) * | 2016-03-04 | 2019-01-25 | 张广睿 | A kind of processing method of document text |
| CN105760368A (en) * | 2016-03-11 | 2016-07-13 | 张广睿 | Deep processing method for characters of document |
| CN105760368B (en) * | 2016-03-11 | 2019-02-12 | 张广睿 | A kind of deep treatment method of document text |
| CN105677643A (en) * | 2016-03-14 | 2016-06-15 | 张广睿 | Translation method combining manpower and machine |
| CN106055529B (en) * | 2016-05-27 | 2019-04-23 | 成都优译信息技术有限公司 | The resolution system and its analytic method of text data to be translated in DWG formatted file |
| CN106021242B (en) * | 2016-05-27 | 2019-04-23 | 成都优译信息技术有限公司 | DWG format drawing interpretation write back data system and its write-back method |
| CN106021197A (en) * | 2016-05-27 | 2016-10-12 | 成都优译信息技术有限公司 | Translation system of DWG-format files and translation method |
| CN106055529A (en) * | 2016-05-27 | 2016-10-26 | 成都优译信息技术有限公司 | Analytic system of text data to be translated in DWG-format files and analytic method thereof |
| CN106021197B (en) * | 2016-05-27 | 2019-04-23 | 成都优译信息技术有限公司 | The translation system and interpretation method of DWG formatted file |
| CN105975461B (en) * | 2016-05-27 | 2019-04-23 | 成都优译信息技术有限公司 | Increase the method for translation newly in DWG formatted file |
| CN106021242A (en) * | 2016-05-27 | 2016-10-12 | 成都优译信息技术有限公司 | Write-back system of drawing interpretation data in DWG format and write-back method thereof |
| CN105975461A (en) * | 2016-05-27 | 2016-09-28 | 成都优译信息技术有限公司 | Method for newly adding translation in DWG format file |
| CN105975451B (en) * | 2016-05-27 | 2019-04-23 | 成都优译信息技术有限公司 | The processing system and its processing method of DWG formatted file translation data |
| CN105975451A (en) * | 2016-05-27 | 2016-09-28 | 成都优译信息技术有限公司 | Processing system and method for DWG-format-file translation data |
| CN107590140B (en) * | 2017-10-17 | 2020-09-25 | 语联网（武汉）信息技术有限公司 | Document missing item processing method |
| CN107590140A (en) * | 2017-10-17 | 2018-01-16 | 语联网（武汉）信息技术有限公司 | Entry process method is translated in a kind of document leakage |
| CN107885735A (en) * | 2017-11-21 | 2018-04-06 | 语联网（武汉）信息技术有限公司 | A kind of unrelated document translation method and system of form |
| CN107885735B (en) * | 2017-11-21 | 2021-05-04 | 语联网（武汉）信息技术有限公司 | Format-independent document translation method and system |
| CN108563645A (en) * | 2018-04-24 | 2018-09-21 | 成都智信电子技术有限公司 | The metadata interpretation method and device of HIS systems |
| CN108563645B (en) * | 2018-04-24 | 2022-03-22 | 成都智信电子技术有限公司 | Metadata translation method and device of HIS (hardware-in-the-system) |
| CN109446531A (en) * | 2018-09-06 | 2019-03-08 | 语联网（武汉）信息技术有限公司 | Detect the method, apparatus and electronic equipment of translation progress |
| CN109783826A (en) * | 2019-01-15 | 2019-05-21 | 四川译讯信息科技有限公司 | A kind of document automatic translating method |
| CN109783826B (en) * | 2019-01-15 | 2023-11-21 | 四川译讯信息科技有限公司 | Automatic document translation method |
| CN111143074A (en) * | 2019-12-30 | 2020-05-12 | 文思海辉智科科技有限公司 | Method and device for distributing translation files |
| CN111143074B (en) * | 2019-12-30 | 2024-04-09 | 文思海辉智科科技有限公司 | Method and device for distributing translation files |
| CN111144070A (en) * | 2019-12-31 | 2020-05-12 | 北京迈迪培尔信息技术有限公司 | Document parsing translation method and device |
| CN111291575A (en) * | 2020-02-28 | 2020-06-16 | 北京字节跳动网络技术有限公司 | Text processing method and device, electronic equipment and storage medium |
| CN112052648A (en) * | 2020-09-02 | 2020-12-08 | 文思海辉智科科技有限公司 | String translation method and device, electronic equipment and storage medium |
| CN112766003A (en) * | 2021-01-20 | 2021-05-07 | 语联网（武汉）信息技术有限公司 | Document auxiliary translation method and device |
| CN113705158A (en) * | 2021-09-26 | 2021-11-26 | 上海一者信息科技有限公司 | Method for intelligently restoring original text style in document translation |
| CN113705158B (en) * | 2021-09-26 | 2024-05-24 | 上海一者信息科技有限公司 | Method for intelligently restoring original text style in document translation |
| CN114065782A (en) * | 2021-11-08 | 2022-02-18 | 语联网（武汉）信息技术有限公司 | Method for translating word document and keeping original style |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104933041B (en) | 2017-09-01 |
| WO2016206336A1 (en) | 2016-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104933041A (en) | File extraction and reduction method favorable for translation work | |
| CN107463553B (en) | Text semantic extraction, representation and modeling method and system for elementary mathematic problems | |
| CN105138350B (en) | A kind of configuration software internationalizes multilingual implementation method | |
| Nair et al. | Machine translation systems for Indian languages | |
| McCarthy et al. | Marrying universal dependencies and universal morphology | |
| KR20150036041A (en) | Phrase-based dictionary extraction and translation quality evaluation | |
| CN105243056B (en) | A kind of Chinese parsing method and device based on punctuation mark processing | |
| CN105808528A (en) | Document character processing method | |
| Yu et al. | Semi-automatically developing Chinese HPSG grammar from the Penn Chinese Treebank for deep parsing | |
| CN111178088A (en) | Configurable neural machine translation method oriented to XML document | |
| Pradet et al. | Adapting VerbNet to French using existing resources | |
| CN113867694A (en) | Method and system for intelligently generating front-end code | |
| CN112766000A (en) | Machine translation method and system based on pre-training model | |
| CN105068990A (en) | Machine-translation-oriented multi-strategy segmentation method and device of English long sentence | |
| CN106156013A (en) | The two-part machine translation method that a kind of regular collocation type phrase is preferential | |
| CN103092830B (en) | A kind of tune sequence regulation obtaining method and device | |
| CN109947711B (en) | Automatic multi-language file management method in IOS project development process | |
| CN101866331A (en) | Conversion method and device of XML (Extensible Markup Language) documents of different languages | |
| CN113378513A (en) | Method for generating domain-relation-extraction-oriented labeled corpus | |
| CN102629244B (en) | Multi-language work card generating system and method | |
| Mrinalini et al. | Pause-based phrase extraction and effective OOV handling for low-resource machine translation systems | |
| Alkazemi et al. | AccurIT: a prototype of a machine translation engine for English to Arabic translation | |
| CN101067785B (en) | Inserting platform-based resource management method and system | |
| Eckle‐Kohler et al. | UBY‐LMF–Exploring the Boundaries of Language‐Independent Lexicon Models | |
| Zaki et al. | A survey of syntactic parsers of Arabic language |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 430074 East Lake Development Zone, Wuhan, Hubei Province, Optics Valley Software Park in the west, south of Nanhu South Road, Optics Valley Software Park, 2 5 layers 205 Patentee after: Language network (Wuhan) Information Technology Co., Ltd. Address before: 430074, Optics Valley Software Park, East Lake Development Zone, Wuhan, south of Hubei, South Lake Road, Optics Valley Software Park, 2, six, 5, No. 205 Patentee before: Wuhan Transn Information Technology Co., Ltd. |
|
| CP03 | Change of name, title or address |