CN108021559B - Natural language understanding system and semantic analysis method - Google Patents
Natural language understanding system and semantic analysis method Download PDFInfo
- Publication number
- CN108021559B CN108021559B CN201810112700.8A CN201810112700A CN108021559B CN 108021559 B CN108021559 B CN 108021559B CN 201810112700 A CN201810112700 A CN 201810112700A CN 108021559 B CN108021559 B CN 108021559B
- Authority
- CN
- China
- Prior art keywords
- module
- semantic analysis
- grammar
- expression
- natural language
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
Abstract
The invention provides a natural language understanding system, which comprises a semantic analysis module and a processor. The semantic analysis module includes an expression module. The expression module includes a generic portion and a non-generic portion, wherein the non-generic portion includes a parameter list. The processor is used for executing the semantic analysis module so that the semantic analysis module is combined with the general part and the non-general part of the expression module. The semantic analysis module provides a plurality of actual parameters to the general part of the expression module according to the parameter list of the non-general part of the expression module so as to generate grammar rule data. In addition, a semantic analysis method is also provided.
Description
Technical Field
The present invention relates to natural language understanding, and more particularly, to a natural language understanding system and a semantic analysis method.
Background
In the application field of intelligent speech recognition, Natural Language Understanding (NLU) technology is currently an important key technology. The natural language understanding technology can be responsible for extracting key information in a user sentence, and can judge the intention of the user to perform subsequent processing corresponding to the intention of the user. However, in practical applications of the rule-based semantic analysis method, the natural language understanding system needs to design corresponding grammar rules for a large amount of corpora respectively. However, since there are many similar vocabulary structures in the natural language, there are many redundant contents in the corresponding grammar rules, which results in an increase in the workload of compiling the grammar rules and increases the difficulty of maintenance and modification. In view of this, several exemplary embodiments of solutions will be presented below.
Disclosure of Invention
The invention provides a natural language understanding system and a semantic analysis method, which can generate a plurality of grammatical rule data according to an expression module so as to effectively save the workload of compiling grammatical rules by the natural language understanding system.
The natural language understanding system comprises a semantic analysis module and a processor. The semantic analysis module includes an expression module. The expression module includes a generic portion and a non-generic portion. The non-generic part includes a parameter list. The processor is used for executing the semantic analysis module so that the semantic analysis module is combined with the general part and the non-general part of the expression module. The semantic analysis module provides at least one of the plurality of actual parameters to the general part of the expression module according to the parameter list of the non-general part of the expression module to generate at least one grammar rule data.
The semantic analysis method is suitable for a natural language understanding system. The natural language understanding system includes a semantic analysis module. The semantic analysis method comprises the following steps. The semantic analysis module is executed such that the semantic analysis module incorporates a generic portion and a non-generic portion of the expression module, wherein the non-generic portion includes a parameter list. Providing at least one of the plurality of actual parameters to the general part of the expression module according to the parameter list of the non-general part of the expression module to generate at least one grammar rule data. The semantic information corresponding to the corpus data is obtained by comparing the corpus data with at least one grammar rule data through a semantic analysis module.
Based on the above, the natural language understanding system and the semantic analysis method of the present invention can compile the form of the generic part and the non-generic part in the expression module, so that the plurality of pieces of grammar rule data are generated in the non-generic part by combining the generic part of the expression module. Therefore, the natural language understanding system and the semantic analysis method can effectively save the workload of compiling grammar rules by the natural language understanding system and can be convenient for maintenance.
In order to make the aforementioned and other features and advantages of the invention more comprehensible, embodiments accompanied with figures are described in detail below.
Drawings
FIG. 1 is a schematic diagram of a natural language understanding system according to an embodiment of the invention.
FIG. 2 is a schematic diagram of a semantic analysis module according to an embodiment of the invention.
FIG. 3 is a flow chart of a semantic analysis method according to an embodiment of the invention.
Detailed Description
In order that the present invention may be more readily understood, the following detailed description is provided as an illustration of specific embodiments of the invention. Further, wherever possible, the same reference numbers will be used throughout the drawings and the description to refer to the same or like parts.
FIG. 1 is a schematic diagram of a natural language understanding system according to an embodiment of the invention. In the embodiment, a Natural Language Understanding (NLU) system 100 includes a processor 110, a memory 120, and an input device 130. The memory 120 stores a semantic analysis module 121. The processor 110 is coupled to the memory 120 and the input device 130. In this embodiment, the semantic analysis module 121 may be pre-stored in another storage device, and when the processor 110 executes the semantic analysis module 121, the processor 110 reads the another storage device to load the semantic analysis module 121 into the memory 120. The other storage device may be, for example, a Hard Disk Drive (HDD), a Solid State Disk (SSD), an Optical Disk (OD), or the like, and the invention is not limited thereto. In the present embodiment, the processor 110 executes the semantic analysis module 121 to generate grammar rule data.
In the embodiment, the Processor 110 is, for example, a Central Processing Unit (CPU), a System On Chip (SOC), or other Programmable general purpose or special purpose Microprocessor (Microprocessor), a Digital Signal Processor (DSP), a Programmable controller, an Application Specific Integrated Circuit (ASIC), a Programmable Logic Device (PLD), other similar Processing devices, or a combination thereof. It is noted that in the present embodiment, the processor 110 includes a Compiler (Compiler), which can be used to execute various natural language and program compiling operations according to the various embodiments of the present invention.
In the present embodiment, the Memory 120 is, for example, a Dynamic Random Access Memory (DRAM), a Flash Memory (Flash Memory), a Non-Volatile Random Access Memory (NVRAM), or the like. In the present embodiment, the memory 120 is used for storing data, parameters and program modules according to the embodiments of the present invention, and the processor 110 can execute the data, parameters and program modules to implement the systems and methods according to the embodiments of the present invention.
In this embodiment, the input device 130 is configured to receive instruction parameters output by a user. The input device 130 is, for example, a Keyboard (Keyboard), a Voice receiver (Voice receiver), a Microphone (Microphone), or a combination of these devices. The input device 130 may be used to receive voice information or command parameters provided by a user, and the invention is not limited thereto. In the present embodiment, the input device 130 can provide data or parameters to the processor 110 according to the various types of input methods described above.
FIG. 2 is a schematic diagram of a semantic analysis module according to an embodiment of the invention. Refer to fig. 1 and 2. In the present embodiment, the semantic analysis module 121 includes an expression module 122. In the embodiment, the semantic analysis module 121 constructs the expression module 122 according to Context Free Grammar (CFGs). And, the semantic analysis module 121 formulates a grammar rule of the expression module 122 by an Extended background-Naur Form (EBNF). In the present embodiment, the expression module 122 pre-compiles the expression module 122 having a generic portion 123 and a non-generic portion 124. In the embodiment, when the processor 110 executes the semantic analysis module 121, the semantic analysis module 121 combines the general part 123 and the non-general part 124 of the expression module 122 to generate a plurality of syntax rule data 130_1, 130_2 to 130_ N, where N is a positive integer greater than 1.
Specifically, in the present embodiment, the generic part 123 of the expression module 122 includes a grammar template, and this grammar template includes a parameterized production module. The non-generic part 124 includes a parameter list, and the parameter list includes a plurality of actual parameters (actual parameters). In the embodiment, when the processor 110 executes the semantic analysis module 121 to combine the general part 123 and the non-general part 124 of the expression module 122, the semantic analysis module 121 passes the actual parameters in the parameter list to the parameterized formula generation module to generate the grammar rule data 130_1, 130_ 2-130 _ N.
In this embodiment, the parameterized generative model of the grammar template may include formal parameters (formal parameters). That is, when the semantic analysis module 121 is combined with the generic part 123 and the non-generic part 124 of the expression module 122, these actual parameters in the parameter list can be passed to the formal parameters in the parameterized production module. For example, the expression contents of expression module 122 may be as in the following syntax. < word overlap (verb) >: $ verb, $ (verb); < doing something (verb, predicate) >: i want < stopover ($ (verb)) > < receiver > $ (predicate); < recovery >: recent | new; < grammar 1 >: < do something (watch, movie) >; < grammar 2 >: < do something (listen to, pop song) >.
In the above grammar, "< word-overlap (verb) >: $ verbs (verbs) one $ (verbs) "and" < doing something (verbs, predicates) >: i want < stopover ($ (verb)) > < receiver > $ (predict) "to be a parameterized production of the grammar template for the general part 123. "< overlap (verb) >" has a formal parameter "(verb)". "< do something (verb, predict) >" has two formal parameters "(verb)" and "(predict)". In the above syntax, "< syntax 1 >" and "< syntax 2 >" are the non-general part 124 of the expression module 122, and correspond to the above "< doing something (verb) >". "< grammar 1 >" has two actual parameters "see" and "movie". "< grammar 2 >" has two actual parameters "listen" and "pop song". In this example, "< grammar 1 >" and "< grammar 2 >" have verb (verb) and predicate (predicate) actual parameters, respectively.
That is, the semantic analysis module 121 can generate two grammar rules according to the expression contents of the expression module 122. According to "< grammar 1 >", one of the two grammar rules is "i want to see a < receiver > movie; < recovery >: recent | new ". According to "< grammar 2 >", the other of the two grammar rules is "i want to listen to a < receiver > popular song; < recovery >: recent | new ". In other words, the semantic module 121 does not need to compile two separate expressions corresponding to two grammar rules. In this example, the semantic analysis module 121 only needs to compile an expression module 122 having a general part 123 to obtain the two grammar rules by using the parameterized formula of the grammar template in the general part 123. Therefore, the natural language understanding system 100 of the present embodiment can effectively save the workload of compiling grammar rules.
In one embodiment, the parameterized generative module of the grammar template may also include a positional parameter (positional parameter). That is, when the semantic analysis module 121 is combined with the generic part 123 and the non-generic part 124 of the expression module 122, these actual parameters in the parameter list can be passed to the location parameters in the parameterized production module. For example, "< word-stack >" and "< do something >" described above are parameterized productions of the grammar templates of the general part 123 of the expression module 122. In this example, the grammatical expression of "< word-on >" may be "< word-on >: 1-1 ", and the syntax expression of" < do something > "may be" < do something >: i want < stopover > < receiver > _2 ", where" _1 "and" _2 "may be divided to correspond to the first parameter and the second parameter in the parameter list. Similarly, the semantic analysis module 121 only needs to compile an expression module 122 having a general part 123 to obtain the two grammar rules by using the parameterized formula of the grammar template in the general part 123.
Referring to fig. 1 and fig. 2 again, in the present embodiment, the natural language understanding system 100 may receive the corpus data input by the user through the input device 130, and compare the corpus data to obtain semantic information corresponding to the corpus data. In the present embodiment, the semantic analysis module 121 can generate the grammar rule data 130_1, 130_2 to 130_ N by combining the general part 123 and the non-general part 124 of the expression module 122 according to the above embodiments. In the embodiment, the manner of generating the grammar rule data 130_1, 130_2 to 130_ N by the semantic analysis module 121 may be the same as the macro (macro) expansion manner performed in the preprocessing stage of the C language. The processor 110 can expand the grammar template and record the grammar template in the memory 120 to simultaneously generate the grammar rule data 130_1, 130_ 2-130 _ N through the expression module 122. That is, the memory 120 uses more memory space to record the grammar rule data 130_1, 130_2 to 130_ N of the expanded expression module 122, and compares the grammar rule data 130_1, 130_2 to 130_ N with the corpus data provided by the user to obtain the semantic information corresponding to the corpus data. Therefore, when the natural language understanding system 100 performs the natural language understanding operation, the natural language understanding system 100 has an efficient comparison effect.
However, in one embodiment, the semantic module 121 may generate the grammar rule data 130_1, 130_ 2-130 _ N in a manner similar to a function call (function call) in the C language. That is, the processor 110 retains the above-mentioned grammar templates in the memory 120, and dynamically replaces the actual parameters in the non-generic part 124 into parameterized production modules of the grammar templates in the generic part 123 to produce the grammar rule data 130_1, 130_2 ~ 130_ N one by one via the expression module 122. In other words, during the dynamic replacement of these actual parameters into parameterized production modules, the comparison is performed immediately every time the actual parameters are replaced. Thus, the natural language understanding system 100 may effectively save memory 120 space when the natural language understanding system 100 performs natural language understanding operations.
FIG. 3 is a flow chart of a semantic analysis method according to an embodiment of the invention. Referring to fig. 1 to fig. 3, the semantic analysis method of the present embodiment can be at least applied to the natural language understanding system 100 and the semantic analysis module 121 of the embodiments of fig. 1 and fig. 3. In step S310, the natural language understanding system 100 executes the semantic analysis module 121 such that the semantic analysis module 121 combines the general part 123 and the non-general part 124 of the expression module 122, wherein the non-general part 124 includes a parameter list. In step S320, the natural language understanding system 100 provides a plurality of actual parameters to the generic part 123 of the expression module 122 according to the parameter list of the non-generic part 124 of the expression module 122 to generate the grammar rule data 130_1, 130_2 ~ 130_ N. In step S330, the natural language understanding system 100 compares the corpus data with the grammar rule data 130_1, 130_2 to 130_ N by the semantic analysis module 121 to obtain semantic information corresponding to the corpus data. Therefore, the semantic analysis method of the present embodiment can effectively save the workload of compiling the grammar rules by the natural language understanding system 100.
In addition, the related device features and technical contents of the natural language understanding system 100 of the present embodiment can be obtained according to the contents of the embodiments of fig. 1 and fig. 2 to obtain sufficient teaching, suggestion and implementation descriptions, and thus, the description thereof is omitted.
In summary, the natural language understanding system and the semantic analysis method of the present invention can compile a grammar template in advance in the general part of the expression module. When the natural language understanding system executes the expression module, the natural language understanding system may provide a plurality of actual parameters of the parameter list of the non-common part into the grammar template of the common part to generate a plurality of pieces of grammar rule data. That is, the natural language understanding system and the semantic analysis method of the present invention can generate a plurality of grammar rule data according to the grammar template without compiling a large amount of grammar rule data in advance. Therefore, the natural language understanding system and the semantic analysis method can effectively save the workload of compiling grammar rules by the natural language understanding system and can be convenient for maintenance.
Although the present invention has been described with reference to the above embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention.
[ notation ] to show
100: electronic device
110: processor with a memory having a plurality of memory cells
120: memory device
121: semantic analysis module
122: expression module
123: general part
124: non-universal section
130_1, 130_2, 130_ N: grammar rule data
S310, S320, S330: step (ii) of
Claims (8)
1. A natural language understanding system, comprising:
a semantic analysis module comprising an expression module and the expression module comprising a generic part and a non-generic part, wherein the non-generic part comprises a parameter list; and
a processor configured to execute the semantic module such that the semantic module combines the generic part and the non-generic part of the expression module, and the semantic module provides at least one of a plurality of actual parameters to the generic part of the expression module according to the parameter list of the non-generic part of the expression module to generate at least one grammar rule data;
a memory coupled to the processor and loaded with the semantic analysis module by the processor when the processor executes the semantic analysis module,
wherein the semantic analysis module generates a plurality of grammar rule data, and compares the corpus data with the grammar rule data to obtain semantic information corresponding to the corpus data,
wherein the semantic analysis module constructs the expression module according to a context free grammar,
wherein the generic portion of the expression module comprises a grammar template and the grammar template comprises a parameterized generative module, wherein when the processor executes the semantic analysis module to combine the generic portion and the non-generic portion of the expression module, the semantic analysis module passes at least one of the plurality of actual parameters into the parameterized generative module to generate the at least one grammar rule data,
wherein the processor retains parameter information form of the grammar template in the memory and dynamically replaces the plurality of actual parameters into the parameterized production modules in the grammar template to produce a plurality of grammar rule data one by one via the expression modules.
2. A natural language understanding system according to claim 1, wherein the parameterized generative module includes formal parameters.
3. A natural language understanding system according to claim 1, wherein the parameterized generative module includes a location parameter.
4. A natural language understanding system according to claim 1, wherein the processor expands the grammar template and records into the memory to simultaneously generate a plurality of grammar rule data via the expression module.
5. A semantic analysis method applied to a natural language understanding system, the natural language understanding system comprising a semantic analysis module, wherein the semantic analysis method comprises:
executing the semantic analysis module to enable the semantic analysis module to combine a general part and a non-general part of an expression module, wherein the non-general part comprises a parameter list;
providing at least one of a plurality of actual parameters to the generic part of the expression module in accordance with the parameter list of the non-generic part of the expression module to generate at least one grammar rule data; and
comparing the corpus data with the at least one grammar rule data by the semantic analysis module to obtain semantic information corresponding to the corpus data,
wherein the semantic analysis module constructs the expression module according to a context free grammar,
wherein the generic part of the expression module comprises a grammar template and the grammar template comprises a parameterized generative module, wherein the step of executing the semantic module such that the semantic module incorporates the generic part and the non-generic part of the expression module comprises:
passing at least one of said plurality of actual parameters to said parameterized generative module when said semantic analysis module combines said generic part and said non-generic part of said expression module to generate said at least one grammar rule data,
wherein the natural language understanding system further comprises a memory, and the step of generating the at least one grammar rule data comprises:
retaining the parameter information form of the grammar template in the memory, and dynamically replacing the plurality of actual parameters into the parameterized production modules in the grammar template to produce a plurality of grammar rule data one by one via the expression modules.
6. The semantic analysis method according to claim 5, wherein the parameterized generative model comprises formal parameters.
7. The semantic analysis method according to claim 5, wherein the parameterized generative model comprises a location parameter.
8. The semantic analysis method according to claim 5, wherein the natural language understanding system further comprises a memory and the step of generating the at least one grammar rule data comprises:
the grammar template is expanded and recorded into the memory to simultaneously generate a plurality of grammar rule data via the expression module.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810112700.8A CN108021559B (en) | 2018-02-05 | 2018-02-05 | Natural language understanding system and semantic analysis method |
TW107111597A TWI673705B (en) | 2018-02-05 | 2018-04-02 | Natural language understanding system and semantic analysis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810112700.8A CN108021559B (en) | 2018-02-05 | 2018-02-05 | Natural language understanding system and semantic analysis method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108021559A CN108021559A (en) | 2018-05-11 |
CN108021559B true CN108021559B (en) | 2022-05-03 |
Family
ID=62075106
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810112700.8A Active CN108021559B (en) | 2018-02-05 | 2018-02-05 | Natural language understanding system and semantic analysis method |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108021559B (en) |
TW (1) | TWI673705B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109543192B (en) * | 2018-11-30 | 2023-05-05 | 出门问问创新科技有限公司 | Natural language analysis method, device, equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101763211A (en) * | 2009-04-30 | 2010-06-30 | 广东国笔科技股份有限公司 | System for analyzing semanteme in real time and controlling related operation |
CN102262622A (en) * | 2010-05-31 | 2011-11-30 | 国际商业机器公司 | Document processing, template generating and conceptbase generating methods and devices |
CN102768682A (en) * | 2012-06-28 | 2012-11-07 | 用友软件股份有限公司 | Business rule processing device and business rule processing method |
CN103294666A (en) * | 2013-05-28 | 2013-09-11 | 百度在线网络技术(北京)有限公司 | Grammar compiling method, semantic parsing method and corresponding devices |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6675370B1 (en) * | 2000-02-02 | 2004-01-06 | International Business Machines Corporation | System and method for imbedding hyperlinked language grammar notation in a “literate” programming environment |
SG142196A1 (en) * | 2006-11-02 | 2008-05-28 | Crimsonlogic Pte Ltd | System and method for processing language independent natural language statements |
CN101814065B (en) * | 2009-02-23 | 2014-07-30 | 富士通株式会社 | Syntactic analysis device and syntactic analysis method |
CN101894236B (en) * | 2010-07-28 | 2012-01-11 | 北京华夏信安科技有限公司 | Software homology detection method and device based on abstract syntax tree and semantic matching |
CN102609462A (en) * | 2012-01-14 | 2012-07-25 | 杭州安恒信息技术有限公司 | Method for compressed storage of massive SQL (structured query language) by means of extracting SQL models |
CN103871402B (en) * | 2012-12-11 | 2017-10-10 | 北京百度网讯科技有限公司 | Language model training system, speech recognition system and correlation method |
US20150242396A1 (en) * | 2014-02-21 | 2015-08-27 | Jun-Huai Su | Translating method for translating a natural-language description into a computer-language description |
KR101729461B1 (en) * | 2014-04-29 | 2017-04-21 | 라쿠텐 인코포레이티드 | Natural language processing system, natural language processing method, and natural language processing program |
CN106326303B (en) * | 2015-06-30 | 2019-09-13 | 芋头科技(杭州)有限公司 | A kind of spoken semantic analysis system and method |
CN107229616B (en) * | 2016-03-25 | 2020-10-16 | 阿里巴巴集团控股有限公司 | Language identification method, device and system |
CN106020803B (en) * | 2016-05-11 | 2020-12-29 | 深圳市麦斯杰网络有限公司 | Dynamic definition method and device of monitored object template |
CN107340999A (en) * | 2017-01-09 | 2017-11-10 | 北京理工大学 | Software automation method and system and the method in structure natural language understanding storehouse |
-
2018
- 2018-02-05 CN CN201810112700.8A patent/CN108021559B/en active Active
- 2018-04-02 TW TW107111597A patent/TWI673705B/en active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101763211A (en) * | 2009-04-30 | 2010-06-30 | 广东国笔科技股份有限公司 | System for analyzing semanteme in real time and controlling related operation |
CN102262622A (en) * | 2010-05-31 | 2011-11-30 | 国际商业机器公司 | Document processing, template generating and conceptbase generating methods and devices |
CN102768682A (en) * | 2012-06-28 | 2012-11-07 | 用友软件股份有限公司 | Business rule processing device and business rule processing method |
CN103294666A (en) * | 2013-05-28 | 2013-09-11 | 百度在线网络技术(北京)有限公司 | Grammar compiling method, semantic parsing method and corresponding devices |
Also Published As
Publication number | Publication date |
---|---|
TW201935463A (en) | 2019-09-01 |
TWI673705B (en) | 2019-10-01 |
CN108021559A (en) | 2018-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8589163B2 (en) | Adapting language models with a bit mask for a subset of related words | |
US7860719B2 (en) | Disfluency detection for a speech-to-speech translation system using phrase-level machine translation with weighted finite state transducers | |
Ebden et al. | The Kestrel TTS text normalization system | |
US8117022B2 (en) | Method and system for machine understanding, knowledge, and conversation | |
US8812321B2 (en) | System and method for combining speech recognition outputs from a plurality of domain-specific speech recognizers via machine learning | |
US10242670B2 (en) | Syntactic re-ranking of potential transcriptions during automatic speech recognition | |
CN103123590A (en) | Compiling method from intermediate language (IL) program to C language program of instruction list | |
US10732937B2 (en) | Programming by voice | |
US9507852B2 (en) | Techniques for discriminative dependency parsing | |
CN108446266B (en) | Statement splitting method, device and equipment | |
US9658999B2 (en) | Language processing method and electronic device | |
CN108021559B (en) | Natural language understanding system and semantic analysis method | |
US10635859B2 (en) | Natural language recognizing apparatus and natural language recognizing method | |
US9837073B2 (en) | Efficient incremental modification of optimized finite-state transducers (FSTs) for use in speech applications | |
CN107025265B (en) | Search method, device, system and generation method of command converter | |
TWI735541B (en) | Method and device for generating code prompt information | |
Galley et al. | Hybrid natural language generation for spoken dialogue systems | |
KR20120045906A (en) | Apparatus and method for correcting error of corpus | |
US8260614B1 (en) | Method and system for expanding a word graph to a phone graph based on a cross-word acoustical model to improve continuous speech recognition | |
US20180011833A1 (en) | Syntax analyzing device, learning device, machine translation device and storage medium | |
CN109065016B (en) | Speech synthesis method, speech synthesis device, electronic equipment and non-transient computer storage medium | |
TWI675365B (en) | Grammar compiling system and grammar compiling method | |
KR101472029B1 (en) | Natural language-based syntax analysis method using index element and system thereof | |
WO2023228313A1 (en) | Language processing method, language processing device, and program | |
KR960025181A (en) | Dynamic Conversion Method of Search Statements for Korean Information Search |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |