CN107562736A - A kind of caching machine interpretation method and system based on neuron - Google Patents
A kind of caching machine interpretation method and system based on neuron Download PDFInfo
- Publication number
- CN107562736A CN107562736A CN201710664396.3A CN201710664396A CN107562736A CN 107562736 A CN107562736 A CN 107562736A CN 201710664396 A CN201710664396 A CN 201710664396A CN 107562736 A CN107562736 A CN 107562736A
- Authority
- CN
- China
- Prior art keywords
- text
- translation
- server
- backstage
- processing
- 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.)
- Pending
Links
Abstract
The present invention provides a kind of caching machine interpretation method based on neuron, including step:User submits the translation comprising cypher text to ask;Request is committed to backstage text-processing server and carries out Text Pretreatment;Cypher text in asking translation is made pauses in reading unpunctuated ancient writings and cutting processing;Backstage text-processing server is searched in cache whether there is existing translation result;Text-processing server in backstage carries out language material standardization to cypher text;Obtain preliminary translation result;Generate final translation result;Final translation result is sent to front end Website server, and stored to cache.The present invention increases cache mechanism in the Service parts of neuron MT engine, when receiving translation request, first it can be scanned for out of cache, if cache memory has history translation record, the direct output result of meeting, it need not again be translated by translation engine again, greatly improve machine translation server resource utilization and translation efficiency.
Description
Technical field
The present invention relates to neuron machine translation mothod.
Background technology
In neuron machine translation field, the statistical machine translation that the decoding time of translation engine is more traditional is much longer.
Because the decoding time directly influences the commercialization of machine translation system, therefore, neuron MT engine how is improved
Translation efficiency is one of most important research topic in neuron machine translation field.At present, to neuron MT engine
Research also rests on the category of decoder, but training pattern and learning framework problem due to neuron MT engine,
Even if reconstruction decoder, its decoding efficiency still has the very big rising space.
The content of the invention
Technical problems to be solved first of the invention are to provide a kind of caching machine interpretation method based on neuron,
The repetition translation of neuron MT engine can be reduced, improves machine translation server resource utilization and translation efficiency.
The technical proposal for solving the technical problem of the invention is:A kind of caching machine translation based on neuron
Method, comprise the following steps:
(1)User submits the translation comprising cypher text to ask;
(2)The translation request of user is committed to backstage text-processing server and carries out Text Pretreatment by front end Website server;
(3)Cypher text in asking translation is made pauses in reading unpunctuated ancient writings and cutting processing;
(4)Backstage text-processing server is searched in cache whether there is existing translation result, if it is present directly
Connect and translation result is fed back into front end Website server, if it does not exist, then continuing in next step;
(5)Text-processing server in backstage carries out language material standardization to cypher text;
(6)Language material after standardization is committed into machine translation server to be translated, obtains preliminary translation result, and send extremely
Backstage text-processing server;
(7)Text-processing server in backstage reduces to preliminary translation result, generates final translation result;
(8)Text-processing server in backstage sends final translation result to front end Website server, and stores to cache.
Further, Text Pretreatment includes asking included text to carry out the filtering of symbol, mess code translation, makes it
Text formatting meets the form of the affiliated languages of the text, its punctuation mark is met the punctuation mark mark of the affiliated languages of the text
It is accurate.
Further, punctuate and cutting processing include languages identification and punctuate processing, wherein, languages identification first judges translation
The affiliated languages of text, punctuation mark punctuate rule is made pauses in reading unpunctuated ancient writings and cut to cypher text corresponding to languages belonging to for punctuate processing
Office is managed, and is syntagma by cypher text processing.
Further, language material standardization includes participle and escape.
The present invention also provides a kind of translation system that can run above-mentioned interpretation method, and the system includes front end website service
Device, backstage text-processing server, cache and machine translation server, after the output end of front end Website server is connected to
The receiving terminal of platform text server simultaneously is sent to translate solicited message, and the output end of backstage text server is connected to machine and turned over
The receiving terminal and cache of server are translated, and is sent to the translation solicited message by pretreatment, machine translation server
Output end be connected to the receiving terminal of backstage text server and be sent to preliminary translation result, backstage text server it is defeated
Go out to hold the receiving terminal for being connected to front end Website server and cache and be sent to final translation result.
The beneficial effects of the invention are as follows:The present invention is high by increasing in the Service parts of neuron MT engine
Fast caching mechanism, when MT engine receives translation request, first it can be scanned for out of cache, if slow at a high speed
There are history translation record, the direct output result of meeting in depositing, it is not necessary to translated by translation engine, also, completed in translation again again
Afterwards, translation result and some sentence patterns are introduced directly into cache, it is not necessary to repeat to translate via MT engine, this
Invention greatly improves machine translation server resource utilization and translation efficiency.
Brief description of the drawings
Fig. 1 is the flow chart of the present invention.
Embodiment
Referring to the drawings.
The system of the present invention includes front end Website server, backstage text-processing server, cache and machine translation
Server, the output end of front end Website server are connected to the receiving terminal of backstage text server and are sent to translation request letter
Breath, the output end of backstage text server is connected to the receiving terminal and cache of machine translation server, and be sent to through
Cross the translation solicited message of pretreatment, the output end of machine translation server be connected to the receiving terminal of backstage text server and to
It sends preliminary translation result, and the output end of backstage text server is connected to the receiving terminal of front end Website server and delayed at a high speed
Deposit and be sent to final translation result.
The step of being translated using said system is specifically included:
1)User submits the translation comprising cypher text to ask.
Here user refers to the people with machine translation demand, and hardware medium includes page end, the machine of mobile terminal turns over
Translate engine service etc..
2)Cypher text is submitted to backstage text-processing server and carries out Text Pretreatment by front end Website server.
Text Pretreatment refers in text-processing server, and symbol, mess code are carried out by system to text to be translated
Filtering, makes its punctuation mark meet the standard punctuation mark category of the languages.
4)Pretreated cypher text is made pauses in reading unpunctuated ancient writings and cutting is handled.
Punctuate and cutting processing include languages identification and punctuate processing, wherein, languages identification is first judged belonging to cypher text
Languages, punctuate processing punctuation mark punctuate rule corresponding to languages belonging to is made pauses in reading unpunctuated ancient writings by cypher text and cutting processing,
It is syntagma by cypher text processing.
5)Backstage text-processing server carries out fast search in cache, search whether existing identical sentence
Translation result.
1. if it does, directly skipping remaining step, front end Website server is directly returned result to.
2. if it does not exist, then go in next step.
6)The steps such as text-processing server in backstage is segmented to the cypher text after punctuate, escape, such step system
Referred to as language material standardizes.
7)The language material of standardization is submitted into machine translation server to be translated, obtains preliminary translation result.
8)Text-processing server in backstage carries out the operations such as sentence merging, escape reduction to preliminary translation result, and generation is most
Whole translation result.
9)Final translation result is returned to front end Website server by backstage text-processing server, is sent it to simultaneously
Cache is stored.
Claims (5)
1. a kind of caching machine interpretation method based on neuron, it is characterized in that, comprise the following steps:
(1)User submits the translation comprising cypher text to ask;
(2)The translation request of user is committed to backstage text-processing server and carries out Text Pretreatment by front end Website server;
(3)Cypher text in asking translation is made pauses in reading unpunctuated ancient writings and cutting processing;
(4)Backstage text-processing server is searched in cache whether there is existing translation result, if it is present directly
Connect and translation result is fed back into front end Website server, if it does not exist, then continuing in next step;
(5)Text-processing server in backstage carries out language material standardization to cypher text;
(6)Language material after standardization is committed into machine translation server to be translated, obtains preliminary translation result, and send extremely
Backstage text-processing server;
(7)Text-processing server in backstage reduces to preliminary translation result, generates final translation result;
(8)Text-processing server in backstage sends final translation result to front end Website server, and stores to cache.
2. a kind of caching machine interpretation method based on neuron according to claim 1, it is characterized in that, text is pre-
Processing includes asking included text to carry out the filtering of symbol, mess code translation, its text formatting is met belonging to the text
The form of languages, its punctuation mark is set to meet the punctuation mark standard of the affiliated languages of the text.
3. a kind of caching machine interpretation method based on neuron according to claim 1, it is characterized in that, punctuate and
Cutting processing includes languages identification and punctuate processing, wherein, languages identification first judges the affiliated languages of cypher text, punctuate processing root
According to punctuation mark punctuate rule is made pauses in reading unpunctuated ancient writings to cypher text corresponding to affiliated languages and cutting is handled, it is by cypher text processing
Syntagma.
4. a kind of caching machine interpretation method based on neuron according to claim 1, it is characterized in that, language material mark
Standardization processing includes participle and escape.
5. a kind of caching machine translation system based on neuron, it is characterized in that, including front end Website server, backstage text
Present treatment server, cache and machine translation server, the output end of front end Website server are connected to backstage text clothes
The receiving terminal of business device simultaneously is sent to translate solicited message, and the output end of backstage text server is connected to machine translation server
Receiving terminal and cache, and be sent to the translation solicited message by pretreatment, the output end of machine translation server
It is connected to the receiving terminal of backstage text server and is sent to preliminary translation result, the output end connection of backstage text server
To front end Website server receiving terminal and cache and be sent to final translation result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710664396.3A CN107562736A (en) | 2017-08-07 | 2017-08-07 | A kind of caching machine interpretation method and system based on neuron |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710664396.3A CN107562736A (en) | 2017-08-07 | 2017-08-07 | A kind of caching machine interpretation method and system based on neuron |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107562736A true CN107562736A (en) | 2018-01-09 |
Family
ID=60974977
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710664396.3A Pending CN107562736A (en) | 2017-08-07 | 2017-08-07 | A kind of caching machine interpretation method and system based on neuron |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107562736A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109145312A (en) * | 2018-06-29 | 2019-01-04 | 中译语通科技股份有限公司 | A kind of machine translation method based on L2 cache, device, medium and electronic equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101034395A (en) * | 2007-03-30 | 2007-09-12 | 传神联合(北京)信息技术有限公司 | Document waiting for translating processing system and document processing method using same |
US20090287671A1 (en) * | 2008-05-16 | 2009-11-19 | Bennett James D | Support for international search terms - translate as you crawl |
CN102364437A (en) * | 2011-09-22 | 2012-02-29 | 厦门游家网络有限公司 | Multi-language site development system and implementation method thereof |
CN103038763A (en) * | 2010-07-23 | 2013-04-10 | 国际商业机器公司 | On-demand translation of application text |
-
2017
- 2017-08-07 CN CN201710664396.3A patent/CN107562736A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101034395A (en) * | 2007-03-30 | 2007-09-12 | 传神联合(北京)信息技术有限公司 | Document waiting for translating processing system and document processing method using same |
US20090287671A1 (en) * | 2008-05-16 | 2009-11-19 | Bennett James D | Support for international search terms - translate as you crawl |
CN103038763A (en) * | 2010-07-23 | 2013-04-10 | 国际商业机器公司 | On-demand translation of application text |
CN102364437A (en) * | 2011-09-22 | 2012-02-29 | 厦门游家网络有限公司 | Multi-language site development system and implementation method thereof |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109145312A (en) * | 2018-06-29 | 2019-01-04 | 中译语通科技股份有限公司 | A kind of machine translation method based on L2 cache, device, medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220058343A1 (en) | Written-modality prosody subsystem in a natural language understanding (nlu) framework | |
CN107608949B (en) | A kind of Text Information Extraction method and device based on semantic model | |
CN104461484B (en) | The implementation method and device of front-end template | |
WO2018205389A1 (en) | Voice recognition method and system, electronic apparatus and medium | |
US10853421B2 (en) | Segmented sentence recognition method and device for human-machine intelligent question answer system | |
CN110765759B (en) | Intention recognition method and device | |
CN101458681A (en) | Voice translation method and voice translation apparatus | |
CN110162767A (en) | The method and apparatus of text error correction | |
CN111310440B (en) | Text error correction method, device and system | |
CN105095182A (en) | Reply information recommendation method and apparatus | |
CN110223675B (en) | Method and system for screening training text data for voice recognition | |
CN110705317B (en) | Translation method and related device | |
CN102523533A (en) | Management method of online video advertisement related to video content | |
CN114757176A (en) | Method for obtaining target intention recognition model and intention recognition method | |
CN104679735A (en) | Pragmatic machine translation method | |
CN110704547A (en) | Relation extraction data generation method, model and training method based on neural network | |
CN110134780B (en) | Method, device, equipment and computer readable storage medium for generating document abstract | |
CN116361431A (en) | Model training method, dialogue generating method, electronic equipment and related device | |
CN107562736A (en) | A kind of caching machine interpretation method and system based on neuron | |
CN105956023A (en) | Method and system for rarely-used character library network application | |
US9672819B2 (en) | Linguistic model database for linguistic recognition, linguistic recognition device and linguistic recognition method, and linguistic recognition system | |
CN109359298A (en) | Emoticon recommended method, system and electronic equipment | |
CN104834633A (en) | Cloud translation input method and system | |
CN115455981B (en) | Semantic understanding method, device and equipment for multilingual sentences and storage medium | |
JP2014229275A (en) | Query answering device and method |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180109 |