CN102662953B - With the semantic tagger system and method that input method is integrated - Google Patents
With the semantic tagger system and method that input method is integrated Download PDFInfo
- Publication number
- CN102662953B CN102662953B CN201210052143.8A CN201210052143A CN102662953B CN 102662953 B CN102662953 B CN 102662953B CN 201210052143 A CN201210052143 A CN 201210052143A CN 102662953 B CN102662953 B CN 102662953B
- Authority
- CN
- China
- Prior art keywords
- user
- semantic
- module
- editor
- storage unit
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 239000000284 extract Substances 0.000 claims abstract description 8
- 239000000463 material Substances 0.000 claims description 22
- 238000012790 confirmation Methods 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000013500 data storage Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Machine Translation (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention discloses a kind of semantic tagger system and method integrated with input method, described system comprises: input method module, editor's idle-detection module, message module, semantic category identification administration module and user confirm module, wherein, editor's idle-detection module triggering semantic category identification administration module when detecting that user is in editor's idle condition carries out semantic analysis to the Word message inputted and extracts semantic tagger object and pre-semantic label, confirm that the semantic tagger object that module prompts user extracts automatically to machine and described pre-semantic label are modified and/or confirm by user.The present invention, by being undertaken integrated by input method and semantic tagger, improves acquisition efficiency and the accuracy rate of semantic tagger metadata.
Description
Technical field
The present invention relates to computer digital animation and input field, be specifically related to the semantic tagger system and method integrated with input method.
Background technology
Along with IT technology particularly the developing rapidly of Web2.0 technology, user produces content and (comprises various types of desktop document, and a large amount of online document-model blog etc.) quantity increases every day with surprising rapidity, people carry out to exchange with others' idea of oneself by foregoing, set forth the viewpoint of oneself, even existing product and service evaluated or express complaint suggestion.
Described user produces content all has high value for individual or commercial undertaking, no matter be that real-time tracking analysis or later retrieval are looked back, all need technology can retrieve the content that these produce and facilitate location, it is a kind of method that primitive character in content-based such as keyword indexes for retrieval, but allow the later stage retrieve need to remember these primitive characters, to be a challenge to the memory of final user, people more easily remembers more abstract content on the contrary, for example, certain concrete name of the dish is difficult to allow people remember, but remember that the style of cooking is instead easy.Therefore produce content to above-mentioned user do the summary in semantic angle and mark and will be very beneficial for later stage searching and locating content.
The time period of semantic tagger from mark generation is done to document, is divided in editor and creates and increase after editor.Create in editor and mean increase semantic label in the compiling procedure of document.After editor, increase is then after document completes, and increases semantic label by robotization or semi-automatic mode.For alleviating the workload that people increases and confirms semantic label, increasing semantic label after normally editor popular at present, automatically extracting possible label by machine learning, leave user's confirmation for uncertain.No matter adopt which kind of machine learning algorithm, all need some documents marked of manual creation as training sample, therefore it is unavoidable for manually carrying out a certain amount of semantic tagger, and semantic tagger is a dynamic process simultaneously, and error label work for correction amount is also very huge.These work all need to carry out artificial input and semantic tagger.
As shown in Figure 1, the method comprises existing automatic semanteme marking method:
Steps A, obtain new word paragraph, and be stored in word paragraph storage unit;
Step B, grammatical analysis is carried out to this paragraph, and result is stored in grammatical analysis result storage unit;
Step C, obtain semantic tagger plug-in unit according to the word paragraph stored and grammatical analysis result and analyze corresponding described pre-semantic label, and mark object the most at last and semantic tagger returns.
As a rule, the method is realized by automatic semantic tagger system as shown in Figure 2.Described system comprises application module, grammer processing module and semantic category identification administration module, wherein:
Application module for obtaining new word paragraph, and is stored in word paragraph storage unit;
Grammer processing module is used for carrying out grammatical analysis to this paragraph, and result is stored in grammatical analysis result storage unit;
And semantic category identification administration module is used for obtaining according to the word paragraph stored and grammatical analysis result the described pre-semantic label that semantic tagger plug-in unit analyzes correspondence, and mark object and semantic tagger return the most at last.
Above-mentioned automatic semanteme marking method and system usually terminate the mark of laggard lang justice whole section of copy editor and return, and therefore usually lack the link that user confirms, the error that automatic semantic tagger is occurred is difficult to be revised, and affects the efficiency of semantic tagger.
Therefore how to be fused in editor by mark, to break the whole up into parts, the accuracy rate of the convenience that raising system uses and semantic tagger needs the problem of solution at present badly.
Summary of the invention
The object of the invention is to improve convenience and the accuracy rate that user carries out semantic tagger.
The invention discloses a kind of semantic tagger system integrated with input method, described system comprises:
Input method module, for carrying out text event detection and being stored in by the Word message of input in word paragraph storage unit;
Editor's idle-detection module, for following the tracks of the information of word paragraph storage unit, detecting user and whether being in editor's idle condition, and is in editor idle condition to message module transmission editor idle message with illustrative user when user is in editor's idle condition;
Message module, for sending semantic analysis request message according to described editor's idle message to semantic category identification administration module;
Semantic category identification administration module, it is right that Word message for analyzing described input according to semantic analysis request message extracts the mark comprising pre-mark object and pre-semantic label, by described mark to being saved in pre-mark object and semantic tagger storage unit, and confirm that module sends semantic tagger and confirms request message to user;
User confirms module, for confirming according to semantic tagger to user, request message shows that the option of described pre-mark object and described pre-semantic label is selected for user, user being selected the annotation results after confirming to return and storing as metadata or additional data.
Wherein, described user confirms that module also comprises semantic tagger modified module and semantic tagger confirms module, described semantic tagger modified module is used for showing that the Word message of described pre-mark object and described input is modified to pre-mark object for user to user, and mark user being revised confirmation is stored in annotation results storage unit;
Described semantic tagger confirms that module is used for showing that the option of described pre-semantic label is selected for user to user, user selected the described pre-semantic label after confirming to be stored in annotation results storage unit, and the annotation results in annotation results storage unit is returned as metadata or additional data storage.
Wherein, the acquiescence item of the option of the described pre-semantic label selected for user is for being stored in the pre-semantic label in pre-mark object and semantic tagger storage unit.According to predetermined editor's idle condition, described editor's idle-detection module judges whether user is in editor's idle condition.
Wherein, described system also comprises semantic tagger cloud collection module, user revises and the contextual information of annotation results after confirming and mark object by described semantic tagger cloud collection module, uploads and be stored in the extensive mark language material storage unit of network side after duplicate removal.
Wherein, the language material stored in described extensive mark language material storage unit is trained for language material model at network side or end side and downloads for described semantic category identification administration module.
The invention also discloses a kind of semanteme marking method integrated with input method, described method comprises:
Carry out text event detection and the Word message of input be stored in word paragraph storage unit;
Follow the tracks of the information of word paragraph storage unit, detect user and whether be in editor's idle condition, and be in editor idle condition to message module transmission editor idle message with illustrative user when user is in editor's idle condition;
Semantic analysis request message is sent to semantic category identification administration module according to described editor's idle message;
It is right that the Word message analyzing described input according to semantic analysis request message extracts the mark comprising pre-mark object and pre-semantic label, by described mark to being saved in pre-mark object and semantic tagger storage unit, and confirm that module sends semantic tagger and confirms request message to user;
Confirm to user, request message shows that the option of described pre-mark object and described pre-semantic label is selected for user according to semantic tagger, user selected the annotation results after confirming to return and store as metadata or additional data.
Wherein, user confirms that step comprises further:
Show that the Word message of described pre-mark object and described input is modified to pre-mark object for user to user, mark user being revised confirmation is stored in annotation results storage unit;
Show that the option of described pre-semantic label is selected for user to user, user selected the described pre-semantic label after confirming to be stored in annotation results storage unit, and the annotation results in annotation results storage unit is returned as metadata or additional data storage.
Wherein, the acquiescence item of the option of the described pre-semantic label selected for user is for being stored in the pre-semantic label in pre-mark object and semantic tagger storage unit.Judge whether user is in editor's idle condition according to predetermined editor's idle condition.
Wherein, described method also comprises step: user revised and the contextual information of annotation results after confirming and mark object, upload and be stored in the extensive mark language material storage unit of network side after duplicate removal.
Wherein, described method also comprises: the language material stored in described extensive mark language material storage unit is trained for language material model at network side or end side and downloads for described semantic category identification administration module.
The present invention is by becoming one semantic tagger and input method, achieve and point out user to carry out manual confirmation for automatic semantic analysis result in user's input characters process, substantially increase metadata and obtain efficiency and accuracy rate, simultaneously, add mark object modification and network share and collaboration feature, extend semantic tagger systematic difference scope, further increase the availability of system.
Accompanying drawing explanation
Fig. 1 is the method flow diagram of existing automatic semanteme marking method;
Fig. 2 is the block diagram of existing automatic semantic tagger system;
Fig. 3 is the block diagram of the semantic tagger system integrated with input method of first embodiment of the invention;
Fig. 4 is the process flow diagram of the semanteme marking method integrated with input method of first embodiment of the invention;
Fig. 5 is the schematic diagram that the user of first embodiment of the invention confirms interface;
Fig. 6 is the block diagram of the semantic tagger system integrated with input method of second embodiment of the invention;
Fig. 7 is the schematic diagram that the user of second embodiment of the invention confirms interface;
Fig. 8 is the block diagram of the semantic tagger system integrated with input method of third embodiment of the invention.
Embodiment
The specific embodiment of the present invention is further illustrated below in conjunction with accompanying drawing.
The input of any application program all by means of specific input media, such as Chinese text, just can need Chinese character coding input method, and the information of all inputs all can be input to corresponding application program such as Microsoft Word process software by input method.The present embodiment semantic tagger and input method are carried out integrated in, so just accomplished annotation process to jump out application program, and will mark and apply decoupling zero.By means of Machine Method obtain pre-markup information present to application system before, as select input word equally allow user confirm.Link is confirmed to realize user.When making user use thus, process is stated in semanteme and text event detection combines together, therefore can improve annotating efficiency and accuracy.
Fig. 3 is the block diagram of the semantic tagger system integrated with input method of first embodiment of the invention.Described system comprises, and input method module, user confirm module, editor's idle-detection module, message processing module and semantic category identification administration module.
Wherein, input method module is used for carrying out text event detection, and the Word message of input is stored in word paragraph storage unit.
Editor's idle-detection module runs the information of following the tracks of word paragraph storage unit always, detect user and whether be in editor's idle condition, if user is in editor's idle condition, such as user within a predetermined period of time non-input characters or user input show the punctuation mark (as comma, fullstop, branch etc.) sentence or paragraph being carried out to sense-group segmentation, then edit idle-detection module and send editor's idle message to message module and be in editor's idle condition with illustrative user.
Message module, according to described editor's idle message, sends semantic analysis request message to semantic category identification administration module.
Semantic category identification administration module is according to the word paragraph of semantic analysis request message analyzing stored in word paragraph storage unit and extract all semantic taggers to (comprising semantic tagger object and pre-semantic label), and be saved in pre-mark object and semantic tagger storage unit, and confirm that module sends semantic tagger and confirms request message to user.
User confirms that module comprises semantic tagger and confirms module, semantic tagger confirms according to semantic tagger, module confirms that request message can start user and confirm processing procedure, show that the option of mark object and described pre-semantic label is selected for user to user, default option is wherein the pre-mark label that semantic category identification administration module is stored in pre-mark object and semantic tagger storage unit, user selects the information after confirming to be saved in annotation results storage unit, and returns annotation results as metadata or additional data storage.
Preferably, the mode of Message Transmission can adopt arrange for storing editor's idle message editor's idle message storage unit, for store semantic analysis request message semantic analysis request message storage unit, confirm that the semantic tagger of request message confirms request message storage unit for storing semantic tagger.Each processing module is sent message by the information content that changes above-mentioned message storage and the change of the information content of monitoring corresponding message storage and is obtained message.Such as, editor's idle-detection module detects that user's User Status upgraded when being in editor's idle condition in described editor's idle message storage unit is the free time, message module detects that described editor's idle message storage unit User Status changes into the free time, then the information in update semantics analysis request message storage.
Fig. 4 is the process flow diagram of the semanteme marking method integrated with input method of first embodiment of the invention.Described method comprises:
Step 100, carry out text event detection, the Word message of input is stored in word paragraph storage unit;
Step 200, follow the tracks of the information of word paragraph storage unit, and detect user and whether be in editor's idle condition, if user is in editor's idle condition, then sends editor's idle message to message module and be in editor's idle condition with illustrative user;
Step 300, according to described editor's idle message, send semantic analysis request message to semantic category identification administration module;
Step 400, extract all semantic taggers to (comprising semantic tagger object and pre-semantic label) according to the word paragraph of semantic analysis request message analyzing stored in word paragraph storage unit, and be saved in pre-mark object and semantic tagger storage unit, and confirm that module sends semantic tagger and confirms request message to semantic tagger;
Step 500, confirm that request message starts user and confirms processing procedure according to semantic tagger, the information after user being confirmed to be saved in annotation results storage unit and annotation results to be stored in metadata or additional data.
Below by way of the flow process of semanteme marking method illustrating first embodiment of the invention.
(1) user uses document editor (such as, Microsoft Word editing machine) Edit Document, uses input method to input following content:
L=" I am from Henan, "
(2) edit idle-detection module to judge whether to be in editor's idle condition according to specific policy, such as when user's inputting punctuation mark time, be editor idle, so according to the input in last step, described editor's idle-detection module can trigger editor's idle message.
M
idle={ editor is idle, Word}
(3) message module can produce a semantic analysis request message after trapping this editor's idle message, triggers semantic category identification administration module accordingly.
(4) semantic category identification administration module analyzes the information in L, obtains following semantic analysis result:
R
can={ " place ": " Henan ", start=3, length=2}
(5) semantic analysis result will be delivered to user and confirm module, confirm CMOS macro cell by user and eject the user's acknowledgement window selecting vocabulary similar with input method as shown in Figure 5, this window is divided into two parts, upper part display mark object " Henan ", the option that bottom display semantic tagger is corresponding, such as " name; place name; mechanism's name etc. ", what acquiescence was chosen is type corresponding in R, and this example corresponds to " place name " preferably.
After user confirms, user confirms that module can produce following annotation results and this result is returned to storage unit:
R={ " place ": " Henan " }
Finally confirm that module obtains described annotation results and is stored in corresponding metadata or additional data by user.
In semantic analysis process, automatic classification identification inevitably there will be mistake.Semantic analysis classification identification error is divided into two classes usually, first semantic type profiling error, should be such as name be identified as place name; An other class is semantic tagger Object identifying mistake, should be such as to be triliterally identified as two words.For Error type I, confirm module by the semantic tagger introduced in first embodiment of the invention, can repair.And for error type II, propose the second embodiment of the present invention at this and do to optimize further to this.
The block diagram of the semantic tagger system integrated with input method of second embodiment of the invention as shown in Figure 6.Described system confirms to add semantic tagger modified module in module user on the basis of the first embodiment.In a second embodiment, user confirms that module comprises semantic tagger and confirms module and semantic tagger modified module, according to semantic tagger, described semantic tagger modified module confirms that request message obtains the word paragraph of input and marks object in advance, by the word paragraph of input and pre-mark object and semantic tagger information hybrid rending, show the word paragraph of input simultaneously and mark object in advance, confirmed to mark object by user, and according to the result of user's amendment or confirmation, the mark object of confirmation is stored into annotation results storage unit.Described semantic tagger confirms that module is selected for user for the option showing described pre-semantic label, default option is wherein the pre-mark label that semantic category identification administration module is stored in pre-mark object and semantic tagger storage unit, and user selects the information after confirming to be saved in annotation results storage unit and returns annotation results as metadata store.
Below by way of the flow process of semanteme marking method illustrating second embodiment of the invention.
(1) user is in use document editor (such as, Microsoft Word editing machine), carrys out Edit Document, uses input method to input following content:
L=" I has visited Palace Museum today, "
(2) edit idle-detection module to judge whether to be in editor's idle condition according to specific policy, such as when user's inputting punctuation mark time, be editor idle, so according to the input in last step, described editor's idle-detection module can trigger editor's idle message.
M
idle={ editor is idle, Word}
(3) message module can produce a semantic analysis request message after trapping this editor's idle message, triggers semantic category identification administration module accordingly.
(4) semantic category identification administration module can analyze the information in L, can obtain following semantic analysis result:
R
can={ " mechanism's name ": " the Forbidden City ", start=5, length=2}
(5) user confirms that module obtains the Word message of semantic analysis result and user's input, eject user's acknowledgement window as shown in Figure 7, this window is divided into two parts, upper part display marks object " the Forbidden City " and its contextual information in advance, wherein mark object in advance by the highlighted display of highlighted subwindow, the reference position of this highlighted subwindow is all adjustable, user can revise mark object by revising this highlighted subwindow, and the option that bottom display semantic tagger is corresponding, such as " name, place name, mechanism's name etc. ", what acquiescence was chosen is pre-semantic label in semantic analysis result, this example corresponds to " mechanism's name " preferably.
If user thinks mark, object should be " Palace Museum ", namely museum can be added by the position of this highlighted subwindow of amendment, and when after user's confirmation, user confirms that this result is returned to storage unit by following for generation annotation results by module:
R={ " mechanism's name ": " Palace Museum " }
(6) the semantic tagger result confirmed through user is finally confirmed by user that module obtains and is stored in corresponding metadata or additional data.
While guarantee improves manual confirmation efficiency, be that system increases network sharing characteristic, making it possible to multiple-person cooperative work, to share result be also one of demand for semantic tagger system of the present invention.Propose the third embodiment of the present invention at this and further optimization is done to the present invention.
Fig. 8 is the block diagram of the semantic tagger system integrated with input method of the 3rd embodiment.Described system adds semantic tagger cloud collection module on the basis of the second embodiment, user revises and mark language material after confirming by semantic tagger cloud collection module, comprise the contextual information of mark object, upload after duplicate removal and be stored in the extensive mark language material storage unit of network side.Be stored in language material in extensive mark language material storage unit directly to be trained by model trainer at network side and become the language material model of semantic analysis model to semantic category identification administration module and carry out model modification, or language material be distributed to language material is trained to language material model thus implementation model by semantic category identification administration module renewal by the model trainer embedded in this module.
The present invention is by becoming one semantic tagger and input method, achieve and point out user to carry out manual confirmation for automatic semantic analysis result in user's input characters process, the metadata substantially increasing user obtains efficiency, simultaneously, add mark object modification and network share and collaboration feature, extend semantic tagger systematic difference scope, achieve the possibility obtaining high-quality metadata language material in enormous quantities, further increase the availability of system.
Above are only preferred embodiment of the present invention and institute's application technology principle, be anyly familiar with those skilled in the art in the technical scope that the present invention discloses, the change that can expect easily or replacement, all should be encompassed in protection scope of the present invention.
Claims (9)
1. a semantic tagger system integrated with input method, described system comprises:
Input method module, for carrying out text event detection and being stored in by the Word message of input in word paragraph storage unit;
Editor's idle-detection module, for following the tracks of the information of word paragraph storage unit, detecting user and whether being in editor's idle condition, and is in editor idle condition to message module transmission editor idle message with illustrative user when user is in editor's idle condition;
Message module, for sending semantic analysis request message according to described editor's idle message to semantic category identification administration module;
Semantic category identification administration module, it is right that Word message for analyzing described input according to semantic analysis request message extracts the mark comprising pre-mark object and pre-semantic label, by described mark to being saved in pre-mark object and semantic tagger storage unit, and confirm that module sends semantic tagger and confirms request message to user;
User confirms module, for confirming according to semantic tagger to user, request message shows that the option of described pre-mark object and described pre-semantic label is selected for user, user being selected the annotation results after confirming to return and storing as metadata or additional data.
2. the semantic tagger system that as claimed in claim 1 and input method is integrated, it is characterized in that, described user confirms that module also comprises semantic tagger modified module and semantic tagger confirms module, described semantic tagger modified module is used for showing that the Word message of described pre-mark object and described input is modified to pre-mark object for user to user, and mark user being revised confirmation is stored in annotation results storage unit;
Described semantic tagger confirms that module is used for showing that the option of described pre-semantic label is selected for user to user, user selected the described pre-semantic label after confirming to be stored in annotation results storage unit, and the annotation results in annotation results storage unit is returned as metadata or additional data storage.
3. the semantic tagger system integrated with input method as claimed in claim 1 or 2, is characterized in that, the acquiescence item of the option of the described pre-semantic label selected for user is for being stored in the pre-semantic label marked in advance in object and semantic tagger storage unit;
According to predetermined editor's idle condition, described editor's idle-detection module judges whether user is in editor's idle condition.
4. the semantic tagger system that as claimed in claim 1 or 2 and input method is integrated, it is characterized in that, described system also comprises semantic tagger cloud collection module, user revises and the contextual information of annotation results after confirming and mark object by described semantic tagger cloud collection module, uploads and be stored in the extensive mark language material storage unit of network side after duplicate removal.
5. the semantic tagger system that as claimed in claim 4 and input method is integrated, it is characterized in that, the language material stored in described extensive mark language material storage unit is trained for language material model at network side or end side and downloads for described semantic category identification administration module.
6. a semanteme marking method integrated with input method, described method comprises:
Carry out text event detection and the Word message of input be stored in word paragraph storage unit;
Follow the tracks of the information of word paragraph storage unit, detect user and whether be in editor's idle condition, and transmission editor idle message is in editor's idle condition with illustrative user when user is in editor's idle condition;
Semantic analysis request message is sent according to described editor's idle message;
It is right that the Word message analyzing described input according to semantic analysis request message extracts the mark comprising pre-mark object and pre-semantic label, by described mark to being saved in pre-mark object and semantic tagger storage unit, and sends semantic tagger and confirm request message;
Confirm to user, request message shows that the option of described pre-mark object and described pre-semantic label is selected for user according to semantic tagger, user selected the annotation results after confirming to return and store as metadata or additional data.
7. the semanteme marking method that as claimed in claim 6 and input method is integrated, it is characterized in that, user confirms that step comprises further:
Show that the Word message of described pre-mark object and described input is modified to pre-mark object for user to user, annotation results user being revised confirmation is stored in annotation results storage unit;
Show that the option of described pre-semantic label is selected for user to user, user selected the described pre-semantic label after confirming to be stored in annotation results storage unit, and the annotation results in annotation results storage unit is returned as metadata or additional data storage.
8. the semanteme marking method integrated with input method as claimed in claims 6 or 7, is characterized in that, the acquiescence item of the option of the described pre-semantic label selected for user is for being stored in the pre-semantic label in pre-mark object and semantic tagger storage unit; And
Judge whether user is in editor's idle condition according to predetermined editor's idle condition.
9. the semanteme marking method integrated with input method as claimed in claims 6 or 7, it is characterized in that, described method also comprises step:
User is revised and the contextual information of annotation results after confirming and mark object, upload after duplicate removal and be stored in the extensive mark language material storage unit of network side.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210052143.8A CN102662953B (en) | 2012-03-01 | 2012-03-01 | With the semantic tagger system and method that input method is integrated |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210052143.8A CN102662953B (en) | 2012-03-01 | 2012-03-01 | With the semantic tagger system and method that input method is integrated |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102662953A CN102662953A (en) | 2012-09-12 |
| CN102662953B true CN102662953B (en) | 2016-04-06 |
Family
ID=46772444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210052143.8A Active CN102662953B (en) | 2012-03-01 | 2012-03-01 | With the semantic tagger system and method that input method is integrated |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102662953B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105068999A (en) * | 2015-08-14 | 2015-11-18 | 浪潮集团有限公司 | Method and apparatus for identifying amended entity words |
| CN109683773B (en) * | 2017-10-19 | 2021-01-22 | 北京国双科技有限公司 | Corpus labeling method and apparatus |
| CN109753976B (en) * | 2017-11-01 | 2021-03-19 | 中国电信股份有限公司 | Corpus labeling device and method |
| CN110807486B (en) * | 2019-10-31 | 2022-09-02 | 北京达佳互联信息技术有限公司 | Method and device for generating category label, electronic equipment and storage medium |
| CN113127635B (en) * | 2019-12-31 | 2024-04-02 | 阿里巴巴集团控股有限公司 | Data processing method, device and system, storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1936892A (en) * | 2006-10-17 | 2007-03-28 | 浙江大学 | Image content semanteme marking method |
| CN101216819A (en) * | 2007-12-28 | 2008-07-09 | 北京邮电大学 | Name card information Chinese to English automatic translation method based on domain ontology |
| CN101334796A (en) * | 2008-02-29 | 2008-12-31 | 浙江师范大学 | Personalized and synergistic integration network multimedia search and enquiry method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7610306B2 (en) * | 2003-06-30 | 2009-10-27 | International Business Machines Corporation | Multi-modal fusion in content-based retrieval |
| CN101075230B (en) * | 2006-05-18 | 2011-11-16 | 中国科学院自动化研究所 | Method and device for translating Chinese organization name based on word block |
-
2012
- 2012-03-01 CN CN201210052143.8A patent/CN102662953B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1936892A (en) * | 2006-10-17 | 2007-03-28 | 浙江大学 | Image content semanteme marking method |
| CN101216819A (en) * | 2007-12-28 | 2008-07-09 | 北京邮电大学 | Name card information Chinese to English automatic translation method based on domain ontology |
| CN101334796A (en) * | 2008-02-29 | 2008-12-31 | 浙江师范大学 | Personalized and synergistic integration network multimedia search and enquiry method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102662953A (en) | 2012-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108932294B (en) | Resume data processing method, device, equipment and storage medium based on index | |
| US10346484B2 (en) | Combining website characteristics in an automatically generated website | |
| US9323731B1 (en) | Data extraction using templates | |
| CN101464905B (en) | Web page information extraction system and method | |
| US8566096B2 (en) | System and method of generating responses to text-based messages | |
| CN103443786B (en) | The machine learning method of the independent task of the parallel layout in identification web browser | |
| US9934220B2 (en) | Content revision using question and answer generation | |
| CN101539904B (en) | Automatic indexing method of quotations | |
| CN107392143A (en) | A kind of resume accurate Analysis method based on SVM text classifications | |
| US20200356363A1 (en) | Methods and systems for automatically generating documentation for software | |
| CN102662953B (en) | With the semantic tagger system and method that input method is integrated | |
| CN104182469B (en) | Method for annotating document and input method system | |
| CN101490668A (en) | Reuse of available source data and localizations | |
| CN110147544B (en) | Instruction generation method and device based on natural language and related equipment | |
| CN110232187A (en) | Enterprise name similarity recognition method, device, computer equipment and storage medium | |
| KR20190020643A (en) | Information mining method, system, electronic device and readable storage medium | |
| CN113076133B (en) | Deep learning-based Java program internal annotation generation method and system | |
| CN102663023A (en) | Implementation method for extracting web content | |
| CN109376868B (en) | Information management system | |
| US11645095B2 (en) | Generating and utilizing a digital knowledge graph to provide contextual recommendations in digital content editing applications | |
| CN110413307B (en) | Code function association method and device and electronic equipment | |
| CN104169912A (en) | Information processing terminal and method, and information management apparatus and method | |
| EP4364044A1 (en) | Automated troubleshooter | |
| CN107493370B (en) | Flow template determining method, flow information identification method and device | |
| US20140075299A1 (en) | Systems and methods for generating extraction models |
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 | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20161227 Address after: 100085 Beijing, Haidian District, No. ten on the ground floor, No. 1, No. 4 international building, No. 2206 Patentee after: Beijing wisdom Technology Co., Ltd. Address before: 100094 Haidian District North Road, Beijing, No. 68 Patentee before: Ni Min |