CN109241542A - A kind of text data processing method for English Translation - Google Patents
A kind of text data processing method for English Translation Download PDFInfo
- Publication number
- CN109241542A CN109241542A CN201810993789.3A CN201810993789A CN109241542A CN 109241542 A CN109241542 A CN 109241542A CN 201810993789 A CN201810993789 A CN 201810993789A CN 109241542 A CN109241542 A CN 109241542A
- Authority
- CN
- China
- Prior art keywords
- translation
- sentence
- data
- word
- english
- 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.)
- Withdrawn
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
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
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 discloses a kind of text data processing methods for English Translation, include the following steps: the text information data to be translated being divided into as unit of sentence, it is then based on the identification that retrieval model completes characteristic item in text information, characteristic item if it exists, this article notebook data is then delivered to human translation module/special translation module to translate, if it does not exist, text information is then divided by the several modules being made of word, phrase based on preset English Translation rule, and completes the acquisition of each word, phrase queueing discipline in text information；Corresponding translation data are inquired in the local database as querying condition using word, phrase, are then based on queueing discipline, the corresponding translation result of the data inquired is arranged, and export sentence translation result；Complete the integration without feature sentence Yu the translation result for having feature sentence, output to client.The invention avoids the mistakes of tense when translation and word order, while can be with the translation blind area of reduction system.
Description
Technical field
The present invention relates to English Translation technical fields, and in particular to a kind of text data processing side for English Translation
Method.
Background technique
It is also increasing to the translation demand of English file with deepening continuously for international exchange, promote large quantities of English
The appearance of the tool of language translation, these English Translation tools are generally divided into online version and city edition, regardless of online version and local
Version is all that search translation is translated in the database, and the translation that the appearance of these translation tools greatly meets user needs
It asks, to translation efficiency is improved, social progress is pushed to contribute.
And since the grammer of English, rule are numerous, needs can be not necessarily exactly matched in the database of translation tool
The sentence of translation is essentially all that sentence to be translated is carried out one-to-one word translation, and tense and word order are wrong frequent occurrence
Accidentally, it and translates stiff, is not achieved in translation and often says the translation brief that fidelity, fluency, elegance.The use of english foundation is also needed at this time
Family carries out check and correction sentence by sentence, makes word order in order, adjusts tense, reorganizes language according to the knowledge of grammar of oneself, these are for English
Just seem helpless for the user of language basis difference.
Summary of the invention
To solve the above problems, the present invention provides a kind of text data processing methods for English Translation.
To achieve the above object, the technical scheme adopted by the invention is as follows:
A kind of text data processing method for English Translation, includes the following steps:
S1, be split data to be translated, identify it is described it is data to be translated in punctuate, using fullstop as division position,
Obtain the text information as unit of sentence；
S2, the identification that characteristic item in the text information is completed based on preset retrieval model, the characteristic item if it exists,
This article notebook data is then delivered to human translation module/special translation module to translate, if it does not exist the characteristic item, then into
Enter step S3；
S3, based on preset English Translation rule by the text information be divided into be made of word, phrase it is several
Module, and complete the acquisition of each word, phrase queueing discipline in text information；
S4, corresponding translation data are inquired as querying condition using the word, phrase in the local database, are then based on
Each word, phrase queueing discipline in the text information, the corresponding translation result of the data inquired is arranged, and exports sentence
Sub- translation result；
S5, repeat step S3-S4, completing institute, whether there is or not the translations of characteristic item sentence, then by turning over whether there is or not characteristic sentence is sub
It translates and there is translation result/special translation module translation result of the human translation module of feature sentence to carry out integration output to visitor
Family end.
Further, the retrieval model is one of probability retrieval model, Boolean logical mode.
Further, the characteristic item is the English Grammar for needing certain translation.
It further, further include that the sentence for having characteristic item and its corresponding human translation result are stored in special translation money
Expect the step in database.
Further, the special translation module is querying condition in special translation information number using the sentence with characteristic item
According in library carry out closest to data inquiry,
Further, described must not be lower than percent 80, if being lower than percentage closest to the likelihood of data and querying condition
80, then start human translation module.
Further, the step S5 carries out the integration of each translation result based on the position where each sentence.
The invention has the following advantages:
It will be split as needing the English Grammar part of certain translation and conventional translator unit with translation data first, then again
Conventional translator unit is splitted into Word parts and phrase part according to preset English Translation rule, constantly so as to avoid translation
The mistake of state and word order, while certain translation part can be translated by human translation module, on the one hand it can make
It is more accurate to translate, and on the other hand also achieves the update filling of data in database.
Specific embodiment
In order to which objects and advantages of the present invention are more clearly understood, the present invention is carried out with reference to embodiments further
It is described in detail.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to limit this hair
It is bright.
Embodiment 1
A kind of text data processing method for English Translation, includes the following steps:
S1, be split data to be translated, identify it is described it is data to be translated in punctuate, using fullstop as division position,
Obtain the text information as unit of sentence；
S2, the identification that characteristic item in the text information is completed based on preset probability retrieval model, the if it exists spy
Item is levied, then this article notebook data is delivered to special translation module and translated, special translation module is with the sentence with characteristic item
The inquiry closest to data is carried out in special translation information database for querying condition, wherein it is described closest to data with look into
The likelihood of inquiry condition must not be lower than percent 80, if starting human translation module lower than percent 80；It is described if it does not exist
Characteristic item then enters step S3；
S3, based on preset English Translation rule by the text information be divided into be made of word, phrase it is several
Module, and complete the acquisition of each word, phrase queueing discipline in text information；
S4, corresponding translation data are inquired as querying condition using the word, phrase in the local database, are then based on
Each word, phrase queueing discipline in the text information, the corresponding translation result of the data inquired is arranged, and exports sentence
Sub- translation result；
S5, repeat step S3-S4, completing institute, whether there is or not the translations of characteristic item sentence, then by turning over whether there is or not characteristic sentence is sub
It translates and there is translation result/special translation module translation result of the human translation module of feature sentence to carry out integration output to visitor
Family end.
Embodiment 2
A kind of text data processing method for English Translation, includes the following steps:
S1, be split data to be translated, identify it is described it is data to be translated in punctuate, using fullstop as division position,
Obtain the text information as unit of sentence；
S2, the identification that characteristic item in the text information is completed based on preset Boolean logical mode, the if it exists spy
Item is levied, then this article notebook data is delivered to special translation module and translated, special translation module is with the sentence with characteristic item
The inquiry closest to data is carried out in special translation information database for querying condition, wherein it is described closest to data with look into
The likelihood of inquiry condition must not be lower than percent 80, if starting human translation module lower than percent 80；It is described if it does not exist
Characteristic item then enters step S3；
S3, based on preset English Translation rule by the text information be divided into be made of word, phrase it is several
Module, and complete the acquisition of each word, phrase queueing discipline in text information；
S4, corresponding translation data are inquired as querying condition using the word, phrase in the local database, are then based on
Each word, phrase queueing discipline in the text information, the corresponding translation result of the data inquired is arranged, and exports sentence
Sub- translation result；
S5, repeat step S3-S4, completing institute, whether there is or not the translations of characteristic item sentence, then by turning over whether there is or not characteristic sentence is sub
It translates and there is translation result/special translation module translation result of the human translation module of feature sentence to carry out integration output to visitor
Family end.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the principle of the present invention, it can also make several improvements and retouch, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (7)
1. a kind of text data processing method for English Translation, which comprises the steps of:
S1, be split data to be translated, identify it is described it is data to be translated in punctuate obtained using fullstop as division position
Text information as unit of sentence；
S2, the identification that characteristic item in the text information is completed based on preset retrieval model, the characteristic item, then will if it exists
This article notebook data is delivered to human translation module/special translation module and is translated, if it does not exist the characteristic item, then enters step
Rapid S3；
S3, the text information is divided by the several modules being made of word, phrase based on preset English Translation rule,
And complete the acquisition of each word, phrase queueing discipline in text information；
S4, corresponding translation data are inquired as querying condition using the word, phrase in the local database, are then based on described
Each word, phrase queueing discipline in text information, the corresponding translation result of the data inquired is arranged, and output sentence turns over
Translate result；
S5, repeat step S3-S4, completing institute, whether there is or not the translations of characteristic item sentence, then by whether there is or not the translation of characteristic sentence and
There is translation result/special translation module translation result of the human translation module of feature sentence to carry out integration output to client
End.
2. a kind of text data processing method for English Translation as described in claim 1, which is characterized in that the retrieval
Model is one of probability retrieval model, Boolean logical mode.
3. a kind of text data processing method for English Translation as described in claim 1, which is characterized in that the feature
Item is the English Grammar for needing certain translation.
4. a kind of text data processing method for English Translation as described in claim 1, which is characterized in that further include by
There are the sentence of characteristic item and its corresponding human translation result to be stored in step in special translation information database.
5. a kind of text data processing method for English Translation as described in claim 1, which is characterized in that described special
Translation module carries out looking into closest to data by querying condition of the sentence with characteristic item in special translation information database
It askes.
6. a kind of text data processing method for English Translation as claimed in claim 5, which is characterized in that described most to connect
The likelihood of nearly data and querying condition must not be lower than percent 80, if starting human translation module lower than percent 80.
7. a kind of text data processing method for English Translation as described in claim 1, which is characterized in that the step
S5 carries out the integration of each translation result based on the position where each sentence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810993789.3A CN109241542A (en) | 2018-08-20 | 2018-08-20 | A kind of text data processing method for English Translation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810993789.3A CN109241542A (en) | 2018-08-20 | 2018-08-20 | A kind of text data processing method for English Translation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109241542A true CN109241542A (en) | 2019-01-18 |
Family
ID=65068869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810993789.3A Withdrawn CN109241542A (en) | 2018-08-20 | 2018-08-20 | A kind of text data processing method for English Translation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109241542A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109829173A (en) * | 2019-01-21 | 2019-05-31 | 中国测绘科学研究院 | A kind of English place name interpretation method and device |
| CN109992753A (en) * | 2019-03-22 | 2019-07-09 | 维沃移动通信有限公司 | A kind of translation processing method and terminal device |
| CN110705321A (en) * | 2019-10-16 | 2020-01-17 | 榆林学院 | Computer aided translation system |
| 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 |
-
2018
- 2018-08-20 CN CN201810993789.3A patent/CN109241542A/en not_active Withdrawn
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109829173A (en) * | 2019-01-21 | 2019-05-31 | 中国测绘科学研究院 | A kind of English place name interpretation method and device |
| CN109829173B (en) * | 2019-01-21 | 2023-09-29 | 中国测绘科学研究院 | English place name translation method and device |
| CN109992753A (en) * | 2019-03-22 | 2019-07-09 | 维沃移动通信有限公司 | A kind of translation processing method and terminal device |
| CN109992753B (en) * | 2019-03-22 | 2023-09-08 | 维沃移动通信有限公司 | Translation processing method and terminal equipment |
| CN110705321A (en) * | 2019-10-16 | 2020-01-17 | 榆林学院 | Computer aided translation system |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241542A (en) | A kind of text data processing method for English Translation | |
| AU2017317878B2 (en) | Error correction method and device for search term | |
| US9342499B2 (en) | Round-trip translation for automated grammatical error correction | |
| US20030061023A1 (en) | Automatic extraction of transfer mappings from bilingual corpora | |
| US9904672B2 (en) | Machine-translation based corrections | |
| US8346819B2 (en) | Enhanced data conversion framework | |
| JP2005535007A (en) | Synthesizing method of self-learning system for knowledge extraction for document retrieval system | |
| Al-Jumaily et al. | A real time Named Entity Recognition system for Arabic text mining | |
| WO2008103894A1 (en) | Automated word-form transformation and part of speech tag assignment | |
| Hollenstein et al. | Compilation of a Swiss German dialect corpus and its application to PoS tagging | |
| Ahmed et al. | Revised n-gram based automatic spelling correction tool to improve retrieval effectiveness | |
| CN105320650B (en) | A kind of machine translation method and its system based on corpus matching and syntactic analysis | |
| CN102486787B (en) | Method and device for extracting document structure | |
| CN110019749B (en) | Method, apparatus, device and computer readable medium for generating VQA training data | |
| Alhanini et al. | The enhancement of arabic stemming by using light stemming and dictionary-based stemming | |
| Pinnis | Context independent term mapper for European languages | |
| Hauser et al. | Unsupervised learning of edit distance weights for retrieving historical spelling variations | |
| CN106569994A (en) | Elevator remote control device | |
| CN102609410B (en) | Authority file auxiliary writing system and authority file generating method | |
| CN102890723A (en) | Example sentence searching method and system | |
| CN103854521A (en) | Suffix induction learning system for English words with vowels or very few consonants serving as initials | |
| Srinivasagan et al. | An automated system for tamil named entity recognition using hybrid approach | |
| Makhija | A study of different stemmer for sindhi language based on devanagari script | |
| Cook | ACRONYM: Acronym CReatiON for You and Me | |
| CN111897958B (en) | Ancient poetry classification method based on natural language processing |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190118 |