CN1489086A - Semantic-stipulated text translation system and method - Google Patents
Semantic-stipulated text translation system and method Download PDFInfo
- Publication number
- CN1489086A CN1489086A CNA021314128A CN02131412A CN1489086A CN 1489086 A CN1489086 A CN 1489086A CN A021314128 A CNA021314128 A CN A021314128A CN 02131412 A CN02131412 A CN 02131412A CN 1489086 A CN1489086 A CN 1489086A
- Authority
- CN
- China
- Prior art keywords
- semantic
- unified coding
- translation
- convention
- symbol
- 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
- 238000013519 translation Methods 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000014616 translation Effects 0.000 claims abstract description 93
- 230000003993 interaction Effects 0.000 claims abstract description 25
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 239000000463 material Substances 0.000 claims description 8
- 239000007787 solid Substances 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 3
- 206010028916 Neologism Diseases 0.000 claims description 2
- 238000004891 communication Methods 0.000 abstract description 12
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 6
- 238000012546 transfer Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 2
- 235000017491 Bambusa tulda Nutrition 0.000 description 2
- 241001330002 Bambuseae Species 0.000 description 2
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 2
- 239000011425 bamboo Substances 0.000 description 2
- 230000003796 beauty Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000021615 conjugation Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- COCAUCFPFHUGAA-MGNBDDOMSA-N n-[3-[(1s,7s)-5-amino-4-thia-6-azabicyclo[5.1.0]oct-5-en-7-yl]-4-fluorophenyl]-5-chloropyridine-2-carboxamide Chemical compound C=1C=C(F)C([C@@]23N=C(SCC[C@@H]2C3)N)=CC=1NC(=O)C1=CC=C(Cl)C=N1 COCAUCFPFHUGAA-MGNBDDOMSA-N 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Landscapes
- Machine Translation (AREA)
Abstract
The translation system and method as a natural language translation technique of multiple language general-purpose man-machine interaction can meet following requests: guaranteeing quality for transmission of semantic information; using native language only for man-machine interaction; automatic conversion to translations of multiple languages. The invention is applicable to short message, E-mail, Web page, information translation for databases (for ex. Digital library), multiple language negotiation in E-commerce, multiple language shared BBS as well as remote or face-to-face multiple language communication.
Description
Technical field
The present invention relates to a kind of semantic-stipulated text translation system and method, relate to a kind of full text translation system and method that adopts multi-lingual general semantic convention Unified coding to realize or rather.
Technical background
Develop in full machine translation mothod of reliable quality, be the dream and the pursuit of natural language information treatment technology always, but state-of-art fails to obtain substantive breakthroughs all the time.It is embodied in: full-automatic translation quality is too poor, can not satisfy the most basic semantic information and transmit demand.It is bilingual that supplementary translation requires the user to understand, its using value is limited.The corpus translation only is fit to provide content adaptation service to the relative fixed text, and user's request face is too narrow.And, then all existing question of substance aspect intermediate language design concept and the user learning cost based on the multilingual translation technology of intermediate language, do not see so far to enter practical application.
The full text machine translation mothod that really can enter extensive practicality need satisfy following basic demand: the first, can guarantee the semantic information Transfer Quality.The second, if in translation process, need to carry out man-machine interaction, must be that the user only need grasp a kind of language (such as mother tongue), rather than bilingual.Be worth and want to have widespread usage at internet arena, also need to add one: a man-machine interactive operation can be automatically converted to the multilingual translation, and in other words, this technology should be a kind of multi-lingual general man-machine interaction natural language translation technology.
The objective of the invention is to design a kind of semantic-stipulated text translation system and method that can satisfy above three requirements simultaneously.International application no be PCT/CN99/00046's " open holographic template formula MML man-machine language interpretation method and holographic semantic tagger system " basic skills of this technology has been proposed, the present invention is replenishing the PCT/CN99/00046 patent.
The premiere feature of natural language is semantic communication.Realize the basic premise of semantic communication function, being communication two party has identical agreement to the semanteme and the grammatical function of linguistic notation representative.Therefore, semantic convention is the basic premise that all semantic informations are transmitted.
The premiere feature of natural language mechanical translation also is semantic communication.Mechanical translation can not be as human translation, based on context language environment is accurately analyzed semanteme of the polysemant in the sentence and syntactic information, therefore, carrying out the original text semantic convention by the man-machine interaction means, is to guarantee the unique selectable approach of original text semantic resolution quality.Even, after being converted to linearly aligned translation symbol, also may produce newly-increased ambiguity owing to the original text semantic analysis result that with the sentence is the unit is entirely true.Therefore, only also providing with the sentence at the translation end is the semantic convention result of unit, just may really guarantee the semantic information Transfer Quality of mechanical translation.
The semanteme of natural language symbol has the free and appointed feature: anyone is neologize, old speech new usage even new syntax (it is multifarious, with rapid changepl. never-ending changes and improvements that netspeak develops, and is exactly a good illustration) freely.Therefore, have the machine translation method that widespread usage is worth, must be able to ensure the free and appointed right of user sign semantic.
For the above-mentioned reasons, man-machine interaction semantic convention technology is actually the core of MT technology, the functional objective of this technology should be: ensureing under the prerequisite of user to sign semantic free and appointed right, any original text semantic convention result can be converted to the semantic convention result of any translation.
Summary of the invention
The fundamental difference of Science and Technology is that the task of science is to find objective law, and the task of technology is a utilization objective law solution practical problems.Therefore, the design concept of semantic convention translation technology comes from following natural language objective law:
Recurrence agreement: it is the same with common wordss more than 1,000 and standard syntax any vocabulary to be carried out semantic convention as Longman's English dictionary, and all available its common wordss of any vocabulary of various natural languages (comprising various regular collocation phrases and sentence that surperficial semanteme and actual semanteme are not inconsistent) and standard syntax are to carrying out semantic convention.And a kind of common wordss of natural language and standard syntax can be to the vocabulary and the grammer of other language carry out semantic convention (as writing various bilingual dictionaries) arbitrarily.Therefore, the recurrence agreement is the semantic convention basic law that various natural languages all have.
Circulation agreement: the semantic convention method of various natural languages basic vocabulary commonly used for the circulation agreement (such as: " good " expression makes the people satisfied, the antonym of " bad ").And, also can carry out between basic vocabulary and the non-basic vocabulary synonym semantic circulation agreement (such as U.S.: beautiful, beautiful, good-looking, in see).Therefore, semantic circulation agreement also is the semantic convention basic law that various natural languages all have.
Symbol and notion redundancy: under prerequisite not with reference to context of co-text, if damaged certain symbol does not influence semantic understanding in the sentence, and the reader knows that what symbol damaged be, so, for semantic communication, this symbol belong to redundant symbol (such as: Chinese sentence " that this book is taken back " if in damaged " ", " basis ", " mistake ", write as " that book is brought ", neither influence semantic understanding, the reader knows that also what symbol damaged be).For the semantic communication function that realizes natural language, redundant symbol (the perhaps redundant semantic item of ambiguity symbol) does not need to carry out semantic convention.
Grammer redundancy: if non-existent grammar concept in the A language, in the B language, can correctly add, then for semantic communication, this grammar concept belong to redundant grammar concept (such as: do not have the part of speech notion in the Chinese, when being translated as English, but can correctly add and various conjugations, illustrate that damaged part of speech notion does not influence semantic understanding, and the reader to know damaged be what, otherwise can't correctly add out of thin air).Because the personalized grammar concept in the various natural languages all has the feature of " do not exist, can correctly add " in the B language in the A language, so all belong to redundant grammar concept.In other words, though the grammer system and the complicated and simple degree of various natural languages have very big difference, but having only multi-lingual general syntax notion (different language grammar concept common factor) is the necessary grammer of organizing sentence semantics, therefore has only multi-lingual general syntax notion clearly to arrange.
According to above natural language objective law, can make following inference:
1, the semanteme of all vocabulary symbols of different natural languages can carry out the recurrence agreement by its limited basicvocabulary symbol; The semantic available limited basicvocabulary symbol+general syntax notion of the limited basicvocabulary symbol agreement that circulates.
If the semantic concept of 2 a kind of natural language vocabulary symbols (no matter being that basicvocabulary also is non-basicvocabulary) does not have corresponding symbol in another kind of natural language, the limited basicvocabulary symbol of all available this language of the damaged side of corresponding symbol+general syntax notion is carried out semantic description.
3, the semantic concept union of the limited basicvocabulary of various natural languages and grammar concept are occured simultaneously for finite aggregate, so can carry out unified digital coding.And this Unified coding result can carry out the recursion Unified coding to the necessary semantic information of any natural language sentences and symbol.
According to above principle, realize that technical scheme of the present invention is such: a kind of semantic-stipulated text translation system and method, its feature may further comprise the steps:
A, to provide with the sentence be the necessary semantic information Unified coding of the natural language method of unit;
B, be generated as different natural language vocabulary sign semantic Unified coding dictionaries and general syntax dictionary according to the Unified coding result;
C, on semantic convention man-machine interaction template, what the user selected the language oneself be familiar with is that the unit carries out the semantic convention man-machine interaction with the sentence, the semantic convention result is automatically converted to Unified coding;
D, translation converse routine generate different natural language translations and translation semantic convention result according to original text semantic information Unified coding result automatically with the translation transformation rule;
E, translation browser provide translation transformation result and translation semantic convention result.
Described steps A be that the necessary semantic information Unified coding of the natural language method of unit is responsible for the necessary semantic information in different natural language vocabularies, regular collocation phrase and the sentence symbol is carried out Unified coding with the sentence; Different natural language vocabulary sign semantic Unified coding dictionaries and the general syntax dictionary of described step B is provided by the different natural language vocabulary symbols and the general syntax notion that provide Unified coding and Unified coding to shine upon; It is that the unit carries out the semantic convention man-machine interaction and the semantic convention result is automatically converted to Unified coding that the semantic convention man-machine interaction template of described step C is responsible for the sentence; The translation converse routine of described step D is responsible for adopting the mapping object in semantic Unified coding call by result translation vocabulary sign semantic Unified coding dictionary of original text and the general syntax dictionary, and generates different natural language translations automatically according to the translation transformation rule; The translation browser of described step e is responsible for providing translation and translation semantic convention result to the translation user, to guarantee the semantic information Transfer Quality of translation result.
Described steps A be that the necessary semantic information Unified coding of the natural language method of unit comprises with the sentence:
1, different natural language vocabulary symbols are carried out the semantic concept Unified coding:
1) level encoder:
A, the basicvocabulary of getting any language carry out the semantic looping discription between the basicvocabulary symbol, and the not synonymity of polysemant is carried out semantic looping discription respectively.
B, the semantic concept of different language basis symbol is mated according to sign semantic looping discription result.If occur the vocabulary symbol that semantic concept can not align between the basicvocabulary of different language, then after getting rid of redundancy concept, carry out semantic description with sentential form with the basic symbol that lacks corresponding symbol side.
C, set up semantic Unified coding to the different language basic concept of semantic concept alignment.
2) secondary coding:
A, based on the one-level Unified coding, with the nearly adopted degree and the type of writing, to refer in particular to object be coordinate, and all semantic item of other vocabulary symbol of different language (desirable 20,000 left and right sides words) are carried out the secondary Unified coding respectively, ambiguity item symbol is repeatedly encoded.
B, everyly can not obtain the symbol of Unified coding and the secondary coded object of the senses of a dictionary entry, after getting rid of redundancy concept, rise to the level encoder object.
3) three grades of Unified coding:
Regular collocation phrase, regular collocation sentence to surperficial semanteme and actual semanteme are not inconsistent carry out semantic description with the vocabulary that has carried out a secondary Unified coding with sentential form, realize three grades of Unified coding.
2, the grammar concept common factor of getting any natural language carries out Unified coding.
The content that is generated as different natural language vocabulary sign semantic Unified coding dictionaries according to the Unified coding result of described step B comprises: different language top layer symbol, the senses of a dictionary entry, upper semanteme, Unified coding; The Unified coding of regular collocation phrase and sentence.
The content that is generated as different natural language general syntax dictionaries according to the Unified coding result of described step B comprises: sentence structure, tense, voice, the type of writing.
The semantic convention man-machine interaction method of described step C is as follows:
1, the about solid plate of sentence element of Unified coding is provided, the original text language material is carried out the man-machine interaction of sentence element agreement for different natural language users.
2, the about solid plate of different language vocabulary sign semantic of Unified coding is provided, original text language material symbol is carried out the man-machine interaction of sign semantic agreement for the different natural language users symbol that communicates in one's mother tongue.
3, the about solid plate of grammar concept of Unified coding is provided, the original text language material is carried out the man-machine interaction of grammar concept agreement for the different natural language users symbol that communicates in one's mother tongue.
The about solid plate of the sentence element of described step C is the about solid plate of a kind of space orientation sentence structure, makes the user determine sentence element by the position that drags sentence symbol in template.(is PCT/CN99/00046 " open holographic template formula MML man-machine language interpretation method and holographic semantic tagger system " referring to international application no)
The translation converse routine of described step D comprises: program and the translation transformation rule program of calling institute's mapping object in translation vocabulary sign semantic Unified coding dictionary and the general syntax dictionary with Unified coding.
The translation browser of described step e comprises the translation browser interface and supplies user inquiring translation semantic convention result's browser interface.
Described step C's is the semantic convention of unit with the sentence on the semantic convention template, can realize by retrieval semantic convention corpus automatically; This corpus generates automatically by the following method and calls:
1, each user's original text semantic convention result (comprising original text symbol and Unified coding result) by the memory device, stores of this user terminal, forms the semantic convention corpus that this user exclusively enjoys.
2, carry out the original text semantic convention result of multi-lingual translation conversion by web browser, the server storage device storage by being connected with this browser forms the semantic convention corpus that the user shares.
3, all available different natural language language materials of all users are directly inquired about its semantic convention Unified coding result.
Described step B is generated as different natural language vocabulary sign semantic Unified coding dictionary content update methods according to the Unified coding result and is:
1,, adds up the frequency of utilization of the newly-increased vocabulary symbol (comprising the newly-increased senses of a dictionary entry) of user, regular collocation phrase, sentence automatically by importing the original text Unified coding of translation browser into.
2,, regularly in the semantic convention dictionary for translation of different language version, add neologisms (comprising the semantic item renewal), regular collocation phrase and sentence simultaneously according to the frequency of utilization statistics of newly-increased vocabulary symbol (comprising the newly-increased senses of a dictionary entry), regular collocation phrase, sentence.
Embodiment
Further specify technical scheme of the present invention below in conjunction with embodiment and accompanying drawing:
Fig. 1 is a vocabulary sign semantic agreement Unified coding template synoptic diagram
Fig. 2 is a semantic-stipulated text translation system main flow block diagram
Fig. 3 is a sentence semantics agreement man-machine interaction template synoptic diagram
Fig. 4 is a sentence element agreement man-machine interaction template synoptic diagram
Embodiment
Referring to Fig. 1,
As Figure 1-1, the basicvocabulary of getting Chinese and english carries out the semantic looping discription of basicvocabulary: Chinese: beauty: the people has been seen feel happy, comfortable; English: beauty:qualities that give pleasureto the senses or lift up the mind or spirit; Providing semantic Unified coding is: 0a01;
Shown in Fig. 1-2, with the nearly adopted degree and the type of writing, to refer in particular to object be coordinate, Chinese: the semantic Unified coding of " good-looking " is: 0a01C+1); The semantic Unified coding of English " fair " is: 0a01E
As Figure 1-3, to regular collocation phrase " green bamboo is luxuriant ", carry out semantic description with the vocabulary and the general syntax that carry out a secondary Unified coding: the Mai Tai of bamboo.
It is as follows to be generated as different natural language vocabulary sign semantic Unified coding dictionary content examples according to the Unified coding result:
Chinese top layer symbol: good
The senses of a dictionary entry 1: the people is satisfied with .../upper semanteme (Unified coding)
The senses of a dictionary entry 2: praise, agreement .../upper semanteme (Unified coding)
The senses of a dictionary entry 3: friendly, harmonious .../upper semanteme/(Unified coding)
The senses of a dictionary entry 4: easily .../upper semanteme (Unified coding)
The senses of a dictionary entry 5: very, quite .../upper semanteme (Unified coding)
Referring to Fig. 2,
In Fig. 2, the digitally coded meaning of left side block diagram is the basic step of system's main flow, and the digitally coded meaning of right side block diagram is the related device of system's main flow operation.
Executive system main flow 1, user interface among the calling system device A (as PC, palm PC, mobile phone) and semantic convention translation system application program, input original text letter symbol;
Executive system main flow 2, the semantic Unified coding dictionary of the original text regular collocation among the calling system device B (as the data storehouse memorizer), lexical semantic Unified coding dictionary, general syntax dictionary and application program are carried out original text semantic convention Unified coding automatically;
Executive system main flow 3, original text semantic convention man-machine interaction template (as Fig. 3,4) among the calling system device C (as the data storehouse memorizer), original text regular collocation semanteme Unified coding dictionary, lexical semantic Unified coding dictionary, general syntax dictionary and application program are carried out man-machine interaction affirmation and modification for the original text user to the semantic engagement outcome automatically of original text.
Executive system main flow 4, internet among the calling system device D, Cellular Networks data transmission set carry out the transmission of original text semantic convention Unified coding, the webserver among the calling system device D, PC storer, communication terminal storer) storage original text semantic convention Unified coding;
Executive system main flow 5, the semantic Unified coding dictionary of translation regular collocation among the calling system device E (as the data storehouse memorizer), lexical semantic Unified coding dictionary, general syntax dictionary, translation transformation rule and application program is carried out translation and translation semantic convention result changes automatically;
Executive system main flow 6, the semantic convention translation browser among the calling system device F (as the diverse network communication terminal equipment) carries out translation for the translation user and the semantic convention result browses.
The invention meaning
The present invention is with know-why and man-machine interaction method succinct reliable, that be difficult to eliminate, and providing only needs mother Language can guarantee the full text machine translation current techique of semantic information Transfer Quality alternately.
The present invention can be used for providing note translation, Email translation, info web translation, types of databases (such as digital library) information translation service, can provide the multi-lingual negotiation of ecommerce, multi-lingual interchange special line, Multi-lingual shared BBS belongs to the universal application technology of the multi-lingual communication field of network.
Because for same user, what original text semantic convention of the present invention and translation conversion were called is same Unified coding dictionary and the syntax library of language only need be packed corresponding single language software in the mobile phone, namely can Realize long-range and face-to-face multi-lingual interchange the between any language user in the SMS communication mode.
Claims (10)
1, a kind of semantic-stipulated text translation system and method is characterized in that comprising:
A, to provide with the sentence be the necessary semantic information Unified coding of the natural language method of unit;
B, generate different natural language vocabulary sign semantic Unified coding dictionaries and general syntax dictionary according to the necessary semantic information Unified coding of natural language result;
C, on semantic convention man-machine interaction template, be that the unit carries out the man-machine interaction of original text semantic convention, and original text semantic convention result is automatically converted to the semantic information Unified coding with the sentence;
D, generate different natural language translations and translation semantic convention result automatically according to original text semantic information Unified coding result;
E, translation browser provide translation and translation semantic convention result to browse.
2, semantic-stipulated text translation system according to claim 1 and method, it is characterized in that, described steps A be that the necessary semantic information Unified coding of the natural language method of unit comprises with the sentence: different natural language vocabulary sign semantic notions are carried out one, two, three Unified coding; Described level encoder method is: the basicvocabulary of getting any natural language carries out the interior basicvocabulary sign semantic looping discription of this language, and polysemant not synonymity carries out semantic looping discription respectively; According to basicvocabulary sign semantic looping discription result the semantic concept of the basic symbol of different language is carried out semantic matches.If the semantic concept of A, B natural language basis symbol can not semantic align, then after getting rid of redundancy concept, carry out semantic description with the basicvocabulary symbol that lacks corresponding concept symbols side with sentential form, and the basicvocabulary symbol of different language semantic concept alignment is set up semantic Unified coding; Described secondary coding method is: based on one-level Unified coding result, with the nearly adopted degree and the type of writing, to refer in particular to object be coordinate, and all semantic item of other vocabulary symbol of different language are carried out the secondary Unified coding respectively, ambiguity item symbol is repeatedly encoded; The every vocabulary symbol and senses of a dictionary entry that can not obtain the secondary Unified coding rises to the level encoder object after getting rid of redundancy concept; Described three grades of coding methods are: to regular collocation phrase and sentence, carry out semantic description with the vocabulary symbol and the general syntax that carry out the semantic Unified coding of I and II with sentential form, realize three grades of Unified coding.
3, semantic-stipulated text translation system according to claim 1 and method, it is characterized in that, described steps A be that the necessary syntactic information Unified coding of the natural language method of unit comprises with the sentence: the grammar concept of getting any natural language is occured simultaneously and is carried out the grammar concept Unified coding.
4, semantic-stipulated text translation system according to claim 1 and method, it is characterized in that the content that generates different natural language vocabulary sign semantic Unified coding dictionaries according to the Unified coding result of described step B comprises: different language top layer symbol, senses of a dictionary entry description, upper semanteme, Unified coding; The Unified coding of regular collocation phrase and sentence.Described step B is generated as different natural language general syntax dictionary contents according to the Unified coding result and comprises: sentence structure, tense, voice, the type of writing.
5, semantic-stipulated text translation system according to claim 1 and method, it is characterized in that, the semantic convention man-machine interaction method of described step C comprises: the about solid plate of sentence element of Unified coding is provided, for different natural language users the original text language material is carried out the man-machine interaction of sentence element agreement; The about solid plate of different language vocabulary sign semantic of Unified coding is provided, uses the linguistic notation of oneself being familiar with that original text language material symbol is carried out the semantic convention man-machine interaction for different natural language users; The about solid plate of grammar concept of Unified coding is provided, uses the linguistic notation of oneself being familiar with that the original text language material is carried out the man-machine interaction of grammar concept agreement for different natural language users.
6, semantic-stipulated text translation system according to claim 1 and method, it is characterized in that the translation converse routine of described step D comprises: program and the translation transformation rule program of calling institute's mapping object in translation vocabulary sign semantic Unified coding dictionary and the general syntax dictionary with Unified coding.
7, semantic-stipulated text translation system according to claim 1 and method is characterized in that, the translation browser of described step e comprises the translation browser interface and for the translation semantic convention of translation user inquiring browser interface as a result.
According to claim 1 and 4 described semantic-stipulated text translation system and methods, it is characterized in that 8, described step C's is the automatic semantic convention of unit with the sentence on the semantic convention template, can realize by retrieval semantic convention corpus automatically; This corpus generates by the following method and calls: each user's original text semantic convention Unified coding result by this user's memory device, stores, forms the semantic convention Unified coding corpus that this user exclusively enjoys; By the original text semantic convention Unified coding result that semantic convention translation browser carries out multi-lingual translation conversion, the server storage device storage by being connected with this browser forms the semantic convention corpus that the user shares; The all available different natural language language materials of all users are directly inquired about its semantic convention Unified coding result.
9, according to claim 1 and 3 described semantic-stipulated text translation system and methods, it is characterized in that, the content update method that is generated as different natural language vocabulary sign semantic Unified coding dictionaries according to the Unified coding result of described step B is: by importing the original text Unified coding of translation browser into, add up the frequency of utilization of the newly-increased vocabulary symbol of user and the newly-increased senses of a dictionary entry, newly-increased regular collocation phrase, sentence automatically; According to the frequency of utilization that increases the vocabulary symbol and the newly-increased senses of a dictionary entry, newly-increased regular collocation phrase, sentence newly, in the semantic convention dictionary for translation of different language version, add neologisms (comprising the semantic item renewal), regular collocation phrase and sentence simultaneously.
10, according to claim 1 and 2 described semantic-stipulated text translation system and methods, it is characterized in that, the redundancy criteria of the eliminating redundant symbol of described steps A is: under the prerequisite with reference to context of co-text not, damaged this conceptualization symbol does not influence semantic understanding in the sentence, and the reader knows that what symbol damaged be.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA021314128A CN1489086A (en) | 2002-10-10 | 2002-10-10 | Semantic-stipulated text translation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA021314128A CN1489086A (en) | 2002-10-10 | 2002-10-10 | Semantic-stipulated text translation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1489086A true CN1489086A (en) | 2004-04-14 |
Family
ID=34144923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA021314128A Pending CN1489086A (en) | 2002-10-10 | 2002-10-10 | Semantic-stipulated text translation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1489086A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102650987A (en) * | 2011-02-25 | 2012-08-29 | 北京百度网讯科技有限公司 | Machine translation method and device both based on source language repeat resource |
| CN102650988A (en) * | 2011-02-25 | 2012-08-29 | 北京百度网讯科技有限公司 | Machine translation method and device based on target language repeat resources |
| CN102999486A (en) * | 2012-11-16 | 2013-03-27 | 沈阳雅译网络技术有限公司 | Phrase rule extracting method based on combination |
| CN103593340A (en) * | 2013-10-28 | 2014-02-19 | 茵鲁维夫有限公司 | Natural expression information processing method, natural expression information processing and responding method, equipment and system |
| CN104169948A (en) * | 2012-03-15 | 2014-11-26 | 赛普特系统有限公司 | Methods, apparatus and products for semantic processing of text |
| CN109344413A (en) * | 2018-10-16 | 2019-02-15 | 北京百度网讯科技有限公司 | Translation processing method and apparatus |
| US10394851B2 (en) | 2014-08-07 | 2019-08-27 | Cortical.Io Ag | Methods and systems for mapping data items to sparse distributed representations |
| US10572221B2 (en) | 2016-10-20 | 2020-02-25 | Cortical.Io Ag | Methods and systems for identifying a level of similarity between a plurality of data representations |
| WO2020151652A1 (en) * | 2019-01-23 | 2020-07-30 | 艾肯特公司 | Naturalist intelligence-based natural expression processing method, and response method, device and system, method for training robot, human-computer interaction system, method for training naturalist intelligence-based human-computer interaction system, and end-to-end control method and control system |
| US10885089B2 (en) | 2015-08-21 | 2021-01-05 | Cortical.Io Ag | Methods and systems for identifying a level of similarity between a filtering criterion and a data item within a set of streamed documents |
| US11734332B2 (en) | 2020-11-19 | 2023-08-22 | Cortical.Io Ag | Methods and systems for reuse of data item fingerprints in generation of semantic maps |
| US12147459B2 (en) | 2014-08-07 | 2024-11-19 | Cortical.Io Ag | Methods and systems for mapping data items to sparse distributed representations |
-
2002
- 2002-10-10 CN CNA021314128A patent/CN1489086A/en active Pending
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102650988A (en) * | 2011-02-25 | 2012-08-29 | 北京百度网讯科技有限公司 | Machine translation method and device based on target language repeat resources |
| CN102650987A (en) * | 2011-02-25 | 2012-08-29 | 北京百度网讯科技有限公司 | Machine translation method and device both based on source language repeat resource |
| CN104169948A (en) * | 2012-03-15 | 2014-11-26 | 赛普特系统有限公司 | Methods, apparatus and products for semantic processing of text |
| CN104169948B (en) * | 2012-03-15 | 2017-08-15 | 皮层Io有限公司 | Method, device and product for text semantic processing |
| CN102999486B (en) * | 2012-11-16 | 2016-12-21 | 沈阳雅译网络技术有限公司 | Phrase rule abstracting method based on combination |
| CN102999486A (en) * | 2012-11-16 | 2013-03-27 | 沈阳雅译网络技术有限公司 | Phrase rule extracting method based on combination |
| US9760565B2 (en) | 2013-10-28 | 2017-09-12 | Zili Yu | Natural expression processing method, processing and response method, device, and system |
| WO2015062284A1 (en) * | 2013-10-28 | 2015-05-07 | 茵鲁维夫有限公司 | Natural expression processing method, processing and response method, device, and system |
| US9753914B2 (en) | 2013-10-28 | 2017-09-05 | Zili Yu | Natural expression processing method, processing and response method, device, and system |
| CN103593340A (en) * | 2013-10-28 | 2014-02-19 | 茵鲁维夫有限公司 | Natural expression information processing method, natural expression information processing and responding method, equipment and system |
| CN105723362A (en) * | 2013-10-28 | 2016-06-29 | 余自立 | Natural expression processing method, processing and response method, device, and system |
| US10394851B2 (en) | 2014-08-07 | 2019-08-27 | Cortical.Io Ag | Methods and systems for mapping data items to sparse distributed representations |
| US12147459B2 (en) | 2014-08-07 | 2024-11-19 | Cortical.Io Ag | Methods and systems for mapping data items to sparse distributed representations |
| US10885089B2 (en) | 2015-08-21 | 2021-01-05 | Cortical.Io Ag | Methods and systems for identifying a level of similarity between a filtering criterion and a data item within a set of streamed documents |
| US11714602B2 (en) | 2016-10-20 | 2023-08-01 | Cortical.Io Ag | Methods and systems for identifying a level of similarity between a plurality of data representations |
| US10572221B2 (en) | 2016-10-20 | 2020-02-25 | Cortical.Io Ag | Methods and systems for identifying a level of similarity between a plurality of data representations |
| US11216248B2 (en) | 2016-10-20 | 2022-01-04 | Cortical.Io Ag | Methods and systems for identifying a level of similarity between a plurality of data representations |
| US12141543B2 (en) | 2016-10-20 | 2024-11-12 | Cortical.Io Ag | Methods and systems for identifying a level of similarity between a plurality of data representations |
| CN109344413A (en) * | 2018-10-16 | 2019-02-15 | 北京百度网讯科技有限公司 | Translation processing method and apparatus |
| CN109344413B (en) * | 2018-10-16 | 2022-05-20 | 北京百度网讯科技有限公司 | Translation processing method, translation processing device, computer equipment and computer readable storage medium |
| WO2020151652A1 (en) * | 2019-01-23 | 2020-07-30 | 艾肯特公司 | Naturalist intelligence-based natural expression processing method, and response method, device and system, method for training robot, human-computer interaction system, method for training naturalist intelligence-based human-computer interaction system, and end-to-end control method and control system |
| US11734332B2 (en) | 2020-11-19 | 2023-08-22 | Cortical.Io Ag | Methods and systems for reuse of data item fingerprints in generation of semantic maps |
| US12197485B2 (en) | 2020-11-19 | 2025-01-14 | Cortical.Io Ag | Methods and systems for reuse of data item fingerprints in generation of semantic maps |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1204514C (en) | Method and apparatus for translating between languages | |
| CN101923858B (en) | Real-time and synchronous mutual translation voice terminal | |
| US20020169592A1 (en) | Open environment for real-time multilingual communication | |
| CN101075435A (en) | Intelligent chatting system and its realizing method | |
| CN100595760C (en) | A method, device and input method system for acquiring spoken words | |
| CN1489086A (en) | Semantic-stipulated text translation system and method | |
| CN101174448B (en) | Talking picture playing method and device, method for generating index file of talking picture | |
| WO2002049253A2 (en) | Method and interface for intelligent user-machine interaction | |
| Newell et al. | The rôle of natural language processing in alternative and augmentative communication | |
| CN101079268A (en) | System and method for sign language synthesis and display | |
| CN101957814A (en) | Instant speech translation system and method | |
| CN1250189A (en) | Electronic dictionary with function of processing customary wording | |
| CN1929655A (en) | Mobile phone capable of realizing text and voice conversion | |
| Mo | Design and Implementation of an Interactive English Translation System Based on the Information‐Assisted Processing Function of the Internet of Things | |
| CN1581158A (en) | Chinese / Pin yin / English dictionary | |
| CN101038647A (en) | Network surveying ballot system and implementing method | |
| CN1687925A (en) | Method for realizing bilingual web page searching | |
| CN103577398B (en) | A kind of level machine translation method and system based on predicate-argument structure | |
| CN1111814C (en) | Open holographic template type man-machine conversation language translation method and holographic semantic labeling system | |
| CN1121015C (en) | Intelligent Chinese computer system for the blind | |
| CN1417707A (en) | Natural language semantic information united-coding method | |
| JP2005506635A (en) | Computer controlled coder / decoder not limited by language or method | |
| CN100352291C (en) | Simultaneous interpreting system in mobile communication | |
| CN1570922A (en) | A mode-parameter language translation method and translating system | |
| CN1086486C (en) | Reading sound translator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |