CN105573992A - Real-time translation method and apparatus - Google Patents
Real-time translation method and apparatus Download PDFInfo
- Publication number
- CN105573992A CN105573992A CN201510933733.5A CN201510933733A CN105573992A CN 105573992 A CN105573992 A CN 105573992A CN 201510933733 A CN201510933733 A CN 201510933733A CN 105573992 A CN105573992 A CN 105573992A
- Authority
- CN
- China
- Prior art keywords
- translation
- chinese character
- real time
- character string
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
Abstract
The invention discloses a real-time translation method and apparatus. The method comprises the following steps: step 1, obtaining a text input by a user and a corresponding pinyin string in real time; step 2, segmenting the pinyin string according to all possibilities by taking pinyin of a single Chinese character as a unit, taking candidate Chinese characters corresponding to the pinyin as nodes, forming a grid structure by connecting lines of the candidate Chinese characters, scoring a Chinese character string composed of any segmentation path in the grid by using a language model to obtain candidate results, and selecting an optimal Chinese character string from the candidate results; and step 3, calling a translation algorithm to translate the optimal Chinese character string, and outputting a translation result. Through the real-time translation method and apparatus, the technical problem that the user needs to occasionally perform switching between the text and an online dictionary during real-time translation of the input text is solved.
Description
Technical field
The present invention relates to a kind of real time translating method and device, particularly relate to a kind of real time translating method to input text and device.
Background technology
Along with the development of global economic integration, interchange between cross-cultural, transnational is day by day frequent, exchange way is also tending towards variation, multi-lingual opinion on public affairs, internationalization, and the impact that language difference produces also seems more and more outstanding, and the translation between different language seems increasingly important.
Current, when people need cypher text time, often by means of some online dictionary or translation engine, but the working environment of these resources and user departs from often, user needs handoff scenario frequently, such as: input text in word, but needing to be switched to webpage gets on to search translation.Make translation become efficiency so very low, work together very inconvenient.
Certainly, also there is screen word-selecting instant translation function in some translation software at present, can be user-friendly, but nonetheless, need to input text instant translation time, still need user to stop current input, mouse moved on the words that will intercept, then just there will be instant translation result, still feeling this user has inconvenience.
Summary of the invention
For overcoming the deficiency that above-mentioned prior art exists, the fundamental purpose of the present invention is to provide a kind of real time translating method and device, which solve needing switching between text and online dictionary frequently to user during input text real time translation, avoid leaving the technical matters that operation interface consults other media.
For reaching above-mentioned and other object, the present invention proposes a kind of real time translating method, comprises the steps:
Step one, the text of user in real input and the pinyin string of correspondence;
Step 2, by pinyin string in units of individual Chinese character phonetic according to likely carrying out cutting, with each candidate Chinese character corresponding to phonetic for node, between candidate Chinese character, line forms network, for the Chinese character string that any cutting route in grid is formed, use language model to give a mark, obtain candidate result, in candidate result, select the Chinese character string that optimum;
Step 3, calls the Chinese character string of translation computing to described optimum and translates, and exported by translation result.
Further, also comprised before step 3 and pre-service is carried out to the Chinese character string of the optimum obtained in described step 2, identify the step of the constituent of the Chinese character string of described optimum.
Further, also comprised the steps: before step 3
Check whether once had translation record, if had, then directly return results in this locality.
Further, in step 3, after setting-up time, calling translation computing translating there is no the part translated, and translation result is returned to this locality.
Further, the step calling translation computing after setting-up time comprises:
Create a thread t at main thread after user knocks a keyboard, and record the ID of t;
Timer is set in described thread t, when after n millisecond, checks that whether the ID of thread t is equal with the ID of main thread record;
If equal, illustrate that t is up-to-date thread, then access translating server, if unequal, illustrate that main thread creates again new thread, have updated ID, t is not up-to-date, then exit.
Further, in step 2, described candidate result is preserved in the buffer according to the sequence of marking height, before described candidate result is preserved in the buffer according to the sequence of marking height, inquiry local cache, if there is the described pinyin string of current input in buffer memory, then the result in buffer memory is discharged to first, described candidate result is discharged to after the result in buffer memory according to marking height.
For achieving the above object, the present invention also provides a kind of real time translator, comprising:
Character string acquisition module, for the text of user in real input and the pinyin string of correspondence;
Syllable text conversion module, for just pinyin string in units of individual Chinese character phonetic according to likely carrying out cutting, with each candidate Chinese character corresponding to phonetic for node, between candidate Chinese character, line forms network, for the Chinese character string that any cutting route in grid is formed, use language model to give a mark, obtain candidate result, in candidate result, select the Chinese character string that optimum;
Translation module, calls the Chinese character string of translation computing to this optimum and translates, and exported by translation result.
Further, this real time translator also comprises pretreatment module, carries out pre-service, identify the constituent of described optimum Chinese character string to the Chinese character string of the optimum that described Syllable text conversion module obtains.
Further, described real time translator also comprises translation cache module, checks whether once had translation record, if had, then directly return results for described translation module before calling translation computing in this locality.
Further, described real time translator also comprises and calls control module, carries out translation computing, and translation is returned to this locality for controlling to call described translation module after setting-up time.
Compared with prior art, a kind of real time translating method of the present invention and device can make user without the need to leaving current operating environment, directly obtain translation by input, avoid and leave the trouble that operation interface consults other media,
Thus improve efficiency and improve Consumer's Experience, can be translated content accurately, the present invention simultaneously can check whether once had translation record in this locality, if had, then directly return results, accelerate the speed of real time translation.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of a kind of real time translating method of the present invention;
Fig. 2 is the Syllable text conversion process schematic of the present invention;
Fig. 3 is the configuration diagram of a kind of real time translator of the present invention.
Embodiment
Below by way of specific instantiation and accompanying drawings embodiments of the present invention, those skilled in the art can understand other advantage of the present invention and effect easily by content disclosed in the present specification.The present invention is also implemented by other different instantiation or is applied, and the every details in this instructions also can based on different viewpoints and application, carries out various modification and change not deviating under spirit of the present invention.
Fig. 1 is the flow chart of steps of a kind of real time translating method of the present invention.As shown in Figure 1, a kind of real time translating method of the present invention, comprises the steps:
Step 101, the text of user in real input and the pinyin string of correspondence;
Step 102, by pinyin string in units of individual Chinese character phonetic according to likely carrying out cutting, with each candidate Chinese character corresponding to phonetic for node, between candidate Chinese character, line forms network, for the Chinese character string that any cutting route in grid is formed, use language model to give a mark, obtain candidate result, the Chinese character string that selection one is optimum in candidate result is also recorded in local cache.
As shown in Figure 2, illustrate, by pinyin string according to likely carrying out cutting, forming network, such as: tiananmen can be cut into tian ' an ' men, also can be cut into ti ' an ' an ' men; For any cutting route in grid, use language model to give a mark, finally list candidate according to score height.
Suppose now to use two gram language model (bigramlanguagemodel), under so-called language model can be understood as the prerequisite of N continuous-1 character string appearance, the Probability p (wn|w1 that N number of character occurs, w2 ..., wn-1), N=2 is exactly binary model; First add that <s> character representation character string starts to character string, </s> character representation terminates, then two paths become:
<s>tiananmen</s>
<s>tiananmen</s>
For the marking of Article 1 path, calculate:
p(tian|<s>)*p(an|tian)*p(men|an)*p(</s>|men)
In like manner Article 2 path is:
p(ti|<s>)*p(an|ti)*p(an|an)*p(men|an)*p(</s>|men)
Wherein, the probability of p (wn|wn-1) obtains from corpus.This is the most basic account form, and the present invention is not as limit.
After user have selected candidate kanji character string, pinyin-Hanzi character string is recorded in local cache.
As shown in Figure 2, suppose that 4 phonetics are shurufangfa, and suppose the corresponding candidate's " defeated " of shu, corresponding three candidates " as entering you " of ru, corresponding two candidates " side of putting " of fang, corresponding four candidates of fa " method of sending out is penalized ", each node respectively in corresponding upper figure, one paths is a Chinese character string, as: input method, method is put in input.
Step 103, carries out pre-service to the Chinese character string of the optimum obtained in described step 102, identifies the constituent of described optimum Chinese character string.
Concrete, in order to translate the word that user selects accurately, the Chinese character word string to selecting is needed to carry out pre-service, such as have selected in " Tian An-men ", being exactly so " Tian An-men ", have selected " motion hidden door ", is exactly " motion hidden door ", identify the composition that the inside is special, for translation process below provides more information.
Step 104, calls translation computing and translates pretreated optimum Chinese character string, and exported by translation result, preferably, translation result (translation) is stored in local cache simultaneously.
Preferably, before step 103, also comprise the steps:
Check whether once had translation record, if had, then directly return results in this locality.
Specifically, before calling translation computing, first check whether this locality once had translation record, if had, then never called translation service, directly returned results.Such as, when user inputs same noun repeatedly time, buffer memory can accelerate corresponding speed.
This method is simply described as, the input through keyboard of user is received by client end interface, then the pinyin string of input is converted to Chinese character candidate, when user selects corresponding candidate character, this candidate character is transferred to backstage translation, use the interpretation method that multi-model merges to obtain translation, finally translation is back to client end interface.
Preferably, in a step 102, described candidate result is preserved in the buffer according to the sequence of marking height; More preferably, local cache was inquired about before described candidate result is preserved in the buffer according to the sequence of marking height, if there is the described pinyin string of current input in buffer memory, then the result in buffer memory is discharged to first, described candidate result is discharged to after the result in buffer memory according to marking height.
That is, inquiry local cache, if the pinyin string that there is current input in buffer memory (refers to original character string tiananmen, check whether user once inputted), then the result in buffer memory is discharged to first, described cutting result is discharged to after buffered results, cutting result sorts from high to low according to said process marking, certainly will with the result duplicate removal of buffer memory, if user once inputted, so directly the result of last time is taken out and makes number one, then other result after being listed according to mark size alternatively; If there is no the phonetic of current input in buffer memory, then direct foregoing cutting result to be listed.
After user have selected candidate character, pinyin-Hanzi is recorded in local cache;
Here it should be noted that, described candidate result is preserved in the buffer according to the sequence of marking height, the amount of capacity of buffer memory can be selected according to demand, such as be set as 1000 records, buffer memory is divided into two parts, a district and b district, a district stores N(≤1000 that user inputs recently) bar data (temporally), b district stores the maximum front 1000-N bar record (by number of times) of the number of times of user history input, records storage and be a district or b district in buffer memory, after receiving the pinyin-Hanzi string that user newly inputs:
If all do not had in buffer memory a+b, then add a district, if a district record is full, then cover time that record at most, record input number of times is 1
If existed in buffer memory b, then this record occurrence number+1
If existed in buffer memory a, then this record occurrence number+1, and whether the occurrence number of inquiring about this record is greater than the occurrence number of a certain bar record in b district, if had: if b district record is full, then covers that record in b district, otherwise directly move to b district.
More excellent, in step 103, the constituent of the Chinese character string of described optimum comprises: one or more in word unit, numeral, date, specific place name, name, mechanism's name, spoken language.
Specifically, character string cutting is word unit by Chinese word segmenting;
Normalization: convert numeral, date expression formula to consolidation form, such as: 32 → 32,200->200, March → March, and then facilitate subsequent treatment;
Entity recognition: the name in identification string, place name, mechanism's name, facilitate subsequent treatment;
Spoken identification: the informal written word part identifying the popular word of user's input and so on, facilitates subsequent treatment.
Preferably, at step 104, translation computing can be called again after setting-up time, be specially after user knocks a keyboard and create a thread t at main thread, and record the ID of t, timer is set in described thread t, when after n millisecond, check that whether the ID of thread t is equal with the ID of main thread record, if equal, illustrate that t is up-to-date thread, then access translating server, if unequal, illustrate that main thread creates again new thread, have updated ID, t is not up-to-date, then exit.
Time user knocks keyboard at every turn, candidate word all may change, if candidate change once just starts to call translation service, then can increase the weight of the burden of server, have a strong impact on Consumer's Experience; The present invention adopts the mode of delay+asynchronous call to enter, and after namely user knocks a keyboard, creates a thread t, in t, arranges timer, and when after n millisecond, thread t tests and checks whether oneself is current up-to-date thread, if not, then exit; If so, then translation service is accessed further.
Concrete grammar is as follows:
Thread t is created, the ID of record t at main thread;
T starts timing;
After n millisecond, check that whether the ID of oneself is equal with the ID of main thread record;
If equal, illustrate that t is last thread, namely up-to-date thread, then continue computing;
If unequal, illustrate that main thread creates again new thread, have updated ID, t is not up-to-date, then exit.
More excellent, in step 104, the translation operational method called after setting-up time in translation computing is the mode adopting multiple translation model to merge, and namely according to the pre-processed results of step 103, adopts the mode that multiple translation model merges to translate.The mode that this multiple translation model merges comprises:
Rule-based translation model:
Because normalized content is limited to numeral, date etc., rule-based interpretative system can be adopted, content can be translated accurately like this;
The translation model of Case-based Reasoning:
For entity, spoken vocabulary, the method for Case-based Reasoning is adopted to translate.Using the composition that identifies as query, retrieve in bilingual case library, if retrieved, then return corresponding translation;
For sentence, phrase, the vocabulary translation of routine, the statistical translation model merged is used to translate.
Fig. 3 is the configuration diagram of a kind of real time translator of the present invention.As shown in Figure 3, a kind of real time translator of the present invention, comprising: character string acquisition module 301, Syllable text conversion module 302, pretreatment module 303 and translation module 304.
The pinyin string of the text that character string acquisition module 301 inputs for user in real and correspondence.
Syllable text conversion module 302, for just pinyin string in units of individual Chinese character phonetic according to likely carrying out cutting, with each candidate Chinese character corresponding to phonetic for node, between candidate Chinese character, line forms network, for the Chinese character string that any cutting route in grid is formed, use language model to give a mark, obtain candidate result, the Chinese character string that selection one is optimum in candidate result is preserved in the buffer.Preferably, candidate result is preserved in the buffer according to the sequence of marking height.More preferably, local cache was inquired about before candidate result is preserved in the buffer according to the sequence of marking height, if there is the described pinyin string of current input in buffer memory, then the result in buffer memory is discharged to first, described candidate result is discharged to after the result in buffer memory according to marking height.
Pretreatment module, pre-service is carried out to the Chinese character string of the optimum that Syllable text conversion module 302 obtains, identify the constituent of described optimum Chinese character string, wherein, the constituent of optimum Chinese character string comprises: one or more in word unit, numeral, date, specific place name, name, mechanism's name, spoken language.
Translation module 304, calls translation computing and translates pretreated optimum Chinese character string, and exported by translation result, preferably, translation result (translation) is stored in local cache simultaneously.In the present invention, the translation operational method that translation module 304 adopts is the mode adopting multiple translation model to merge
Preferably, the real time translator of the present invention also comprises translation cache module 305, for checking whether once had translation record in this locality, if had, then directly returns results.
Preferably, the real time translator of the present invention also comprises and calls control module 306, carries out translation computing, and translation is returned to this locality for calling translation module 304 after setting-up time.
More preferably, call control module 306, after setting-up time, call translation module 204 carry out translation computing, concrete mode is: create a thread t at main thread after user knocks a keyboard, and record the ID of t, timer is set in described thread t, when after n millisecond, checks that whether the ID of thread t is equal with the ID of main thread record, if equal, illustrate that t is up-to-date thread, then access translating server, if unequal, illustrate that main thread creates again new thread, have updated ID, t is not up-to-date, then exit.
In sum, a kind of real time translating method of the present invention and device can make user without the need to leaving current operating environment, directly obtain translation by input, thus improve efficiency and improve Consumer's Experience, can be translated content accurately, the present invention simultaneously can check whether once had translation record, if had in this locality, then directly return results, accelerate the speed of real time translation.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not for limiting the present invention.Any those skilled in the art all without prejudice under spirit of the present invention and category, can carry out modifying to above-described embodiment and change.Therefore, the scope of the present invention, should listed by claims.
Claims (10)
1. a real time translating method, comprises the steps:
Step one, the text of user in real input and the pinyin string of correspondence;
Step 2, by pinyin string in units of individual Chinese character phonetic according to likely carrying out cutting, with each candidate Chinese character corresponding to phonetic for node, between candidate Chinese character, line forms network, for the Chinese character string that any cutting route in grid is formed, use language model to give a mark, obtain candidate result, in candidate result, select the Chinese character string that optimum;
Step 3, calls the Chinese character string of translation computing to described optimum and translates, and exported by translation result.
2. a kind of real time translating method as claimed in claim 1, is characterized in that: also comprised before step 3 and carry out pre-service to the Chinese character string of the optimum obtained in described step 2, identify the step of the constituent of the Chinese character string of described optimum.
3. a kind of real time translating method as claimed in claim 2, is characterized in that, also comprised the steps: before step 3
Check whether once had translation record, if had, then directly return results in this locality.
4. a kind of real time translating method as claimed in claim 3, is characterized in that: in step 3, calls translation computing and translates not having the part translated, and translation result is returned to this locality after setting-up time.
5. a kind of real time translating method as claimed in claim 4, is characterized in that, the step calling translation computing after setting-up time comprises:
Create a thread t at main thread after user knocks a keyboard, and record the ID of t;
Timer is set in described thread t, when after n millisecond, checks that whether the ID of thread t is equal with the ID of main thread record;
If equal, illustrate that t is up-to-date thread, then access translating server, if unequal, illustrate that main thread creates again new thread, have updated ID, t is not up-to-date, then exit.
6. a kind of real time translating method as claimed in claim 1, it is characterized in that: in step 2, described candidate result is preserved in the buffer according to the sequence of marking height, before described candidate result is preserved in the buffer according to the sequence of marking height, inquiry local cache, if there is the described pinyin string of current input in buffer memory, then the result in buffer memory is discharged to first, described candidate result is discharged to after the result in buffer memory according to marking height.
7. a real time translator, comprising:
Character string acquisition module, for the text of user in real input and the pinyin string of correspondence;
Syllable text conversion module, for just pinyin string in units of individual Chinese character phonetic according to likely carrying out cutting, with each candidate Chinese character corresponding to phonetic for node, between candidate Chinese character, line forms network, for the Chinese character string that any cutting route in grid is formed, use language model to give a mark, obtain candidate result, in candidate result, select the Chinese character string that optimum;
Translation module, calls the Chinese character string of translation computing to this optimum and translates, and exported by translation result.
8. a kind of real time translator as claimed in claim 7, it is characterized in that: this real time translator also comprises pretreatment module, pre-service is carried out to the Chinese character string of the optimum that described Syllable text conversion module obtains, identifies the constituent of described optimum Chinese character string.
9. a kind of real time translator as claimed in claim 7, it is characterized in that: described real time translator also comprises translation cache module, check whether once had translation record in this locality before calling translation computing for described translation module, if had, then directly return results.
10. a kind of real time translator as claimed in claim 9, is characterized in that: described real time translator also comprises and calls control module, carries out translation computing, and translation is returned to this locality for controlling to call described translation module after setting-up time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510933733.5A CN105573992B (en) | 2015-12-15 | 2015-12-15 | Real-time translation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510933733.5A CN105573992B (en) | 2015-12-15 | 2015-12-15 | Real-time translation method and apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105573992A true CN105573992A (en) | 2016-05-11 |
| CN105573992B CN105573992B (en) | 2017-02-15 |
Family
ID=55884142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510933733.5A Active CN105573992B (en) | 2015-12-15 | 2015-12-15 | Real-time translation method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105573992B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980390A (en) * | 2016-01-18 | 2017-07-25 | 富士通株式会社 | Supplementary translation input method and supplementary translation input equipment |
| CN108959274A (en) * | 2018-06-27 | 2018-12-07 | 维沃移动通信有限公司 | A kind of interpretation method and server of application program |
| CN109032375A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | Candidate text sort method, device, equipment and storage medium |
| CN109921983A (en) * | 2019-03-07 | 2019-06-21 | 上海百途归一智能科技有限公司 | A kind of multilingual chat mobile application |
| CN110262674A (en) * | 2019-06-27 | 2019-09-20 | 北京金山安全软件有限公司 | Chinese character input method and device based on pinyin input and electronic equipment |
| CN113076760A (en) * | 2020-01-03 | 2021-07-06 | 阿里巴巴集团控股有限公司 | Translation method, commodity retrieval method, translation device, commodity retrieval device, electronic equipment and computer storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129423A (en) * | 2010-01-13 | 2011-07-20 | 阿里巴巴集团控股有限公司 | Statement display method and device |
| CN102193643A (en) * | 2010-03-15 | 2011-09-21 | 北京搜狗科技发展有限公司 | Word input method and input method system having translation function |
| US20140172408A1 (en) * | 2012-12-14 | 2014-06-19 | Microsoft Corporation | Text overlay techniques in realtime translation |
| CN104133561A (en) * | 2014-07-31 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Auxiliary information display method and device based on input method |
-
2015
- 2015-12-15 CN CN201510933733.5A patent/CN105573992B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129423A (en) * | 2010-01-13 | 2011-07-20 | 阿里巴巴集团控股有限公司 | Statement display method and device |
| CN102193643A (en) * | 2010-03-15 | 2011-09-21 | 北京搜狗科技发展有限公司 | Word input method and input method system having translation function |
| US20140172408A1 (en) * | 2012-12-14 | 2014-06-19 | Microsoft Corporation | Text overlay techniques in realtime translation |
| CN104133561A (en) * | 2014-07-31 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Auxiliary information display method and device based on input method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980390A (en) * | 2016-01-18 | 2017-07-25 | 富士通株式会社 | Supplementary translation input method and supplementary translation input equipment |
| CN108959274A (en) * | 2018-06-27 | 2018-12-07 | 维沃移动通信有限公司 | A kind of interpretation method and server of application program |
| CN108959274B (en) * | 2018-06-27 | 2022-09-02 | 维沃移动通信有限公司 | Translation method of application program and server |
| CN109032375A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | Candidate text sort method, device, equipment and storage medium |
| CN109921983A (en) * | 2019-03-07 | 2019-06-21 | 上海百途归一智能科技有限公司 | A kind of multilingual chat mobile application |
| CN110262674A (en) * | 2019-06-27 | 2019-09-20 | 北京金山安全软件有限公司 | Chinese character input method and device based on pinyin input and electronic equipment |
| CN110262674B (en) * | 2019-06-27 | 2023-07-18 | 北京金山安全软件有限公司 | Chinese character input method and device based on pinyin input and electronic equipment |
| CN113076760A (en) * | 2020-01-03 | 2021-07-06 | 阿里巴巴集团控股有限公司 | Translation method, commodity retrieval method, translation device, commodity retrieval device, electronic equipment and computer storage medium |
| CN113076760B (en) * | 2020-01-03 | 2024-01-26 | 阿里巴巴集团控股有限公司 | Translation and commodity retrieval method and device, electronic equipment and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105573992B (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11238232B2 (en) | Written-modality prosody subsystem in a natural language understanding (NLU) framework | |
| CN105573992A (en) | Real-time translation method and apparatus | |
| Eshel et al. | Named entity disambiguation for noisy text | |
| US20210004443A1 (en) | Pinning artifacts for expansion of search keys and search spaces in a natural language understanding (nlu) framework | |
| JP2020518870A (en) | Facilitating end-to-end communication with automated assistants in multiple languages | |
| WO2016127677A1 (en) | Address structuring method and device | |
| KR20170106308A (en) | Annotation assistance device and computer program therefor | |
| KR101266361B1 (en) | Automatic translation system based on structured translation memory and automatic translating method using the same | |
| WO2008107305A2 (en) | Search-based word segmentation method and device for language without word boundary tag | |
| JP2001195404A (en) | Phase translation method and system | |
| CN103488752A (en) | POI (point of interest) searching method | |
| JP2018055670A (en) | Similar sentence generation method, similar sentence generation program, similar sentence generation apparatus, and similar sentence generation system | |
| Raza et al. | A review on Urdu language parsing | |
| WO2022148467A1 (en) | Cross-language data enhancement-based word segmentation method and apparatus | |
| US8041556B2 (en) | Chinese to english translation tool | |
| KR101616031B1 (en) | Query Translator and Method for Cross-language Information Retrieval using Liguistic Resources from Wikipedia and Parallel Corpus | |
| JP2006004366A (en) | Machine translation system and computer program for it | |
| CN108153743B (en) | Intelligent off-line translation machine based on similarity | |
| JP4088171B2 (en) | Text analysis apparatus, method, program, and recording medium recording the program | |
| US20230186022A1 (en) | Method and system for finding associations between natural language and computer language | |
| Ramaswamy et al. | Hierarchical feature-based translation for scalable natural language understanding | |
| US20240106776A1 (en) | Sign Language Translation Method And System Thereof | |
| KR102640887B1 (en) | Method and electronic device for generating multilingual website content | |
| CN114020898B (en) | Man-machine automatic dialogue method, device, electronic equipment and storage medium | |
| Rahman et al. | A framework for building a natural language interface for bangla |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100040 middle iron Development Building, No. 20, Shijingshan Road, Shijingshan District, Beijing, 16 layers Patentee after: Chinese translation language through Polytron Technologies Inc Address before: 100040 middle iron Development Building, No. 20, Shijingshan Road, Shijingshan District, Beijing, 16 layers Patentee before: Mandarin Technology (Beijing) Co., Ltd. |