CN112650846B - Question and answer intention knowledge base construction system and method based on question frame - Google Patents
Question and answer intention knowledge base construction system and method based on question frame Download PDFInfo
- Publication number
- CN112650846B CN112650846B CN202110040888.1A CN202110040888A CN112650846B CN 112650846 B CN112650846 B CN 112650846B CN 202110040888 A CN202110040888 A CN 202110040888A CN 112650846 B CN112650846 B CN 112650846B
- Authority
- CN
- China
- Prior art keywords
- question
- sentence
- frame
- answer
- target word
- 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 25
- 238000009411 base construction Methods 0.000 title claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000012300 Sequence Analysis Methods 0.000 claims description 2
- 238000009825 accumulation Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 230000001351 cycling effect Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000006467 substitution reaction Methods 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a question and answer intention knowledge base construction system and method based on a question frame. Comprising the following steps: the data layer comprises a question corpus, a frame element dictionary and a question and answer intention knowledge base; the method is used for storing files, reading and writing files and modifying files; the processing layer comprises a frame element processing module and a question and answer rewriting module and is used for rewriting a question; the application layer comprises a question analysis module and is used for outputting candidate target word strings formed by rewriting the questions. The question and answer intention knowledge base construction system and method based on the question frame improve the problems that in the prior art, the frame elements are difficult to identify and the question and answer form of question analysis cannot be automatically obtained.
Description
Technical Field
The invention relates to the technical field of construction of question and answer intention knowledge bases, in particular to a question and answer intention knowledge base construction system and method based on a question frame.
Background
Sentence intent (sentence frame) is the meaning of sentences in the real world, which is a semantic meaning, and a method of frame semantics (FrameNet) is generally adopted, the name and frame elements of a frame are determined according to the scene where the frame is located, and the target words of the frame are defined according to predicates or verbs in the sentences. This definition of the target word of the whole sentence in a part of the predicate or verb and the determination of the frame element in practice presents the following problems:
(1) The entity ambiguity cannot be resolved and the frame element cannot be identified
Such as "what is the dam 3 well depth", where "dam 3" and "dam 3 well" are both 2 truly existing but disparate types of entities, then the entity in question is exactly "dam 3 well depth" or "dam 3 well depth? This ambiguity problem cannot be resolved at the word level, and the actual intent and elements of the questioner can be corrected out only at the higher sentence level through the knowledge base.
(2) Non-verb sentence unrecognizable frame
English is a language based on verbs, so that the frame and the frame element are successfully identified based on verbs, but the method is clear, but target words cannot be defined when the intention (frame) of a question is identified, so that the frame and the frame element of the question cannot be identified, and analysis of the question and the answer cannot be performed.
For example, "depth of hole of dam 3", the meaning of this sentence in question and answer scene is very clear, namely "depth of hole" of each well that this gas gathering station of question "dam 3" contains, but there is no verb but noun in question, NLP can't discern the frame and frame element of this sentence.
(3) The frame cannot be identified without the sequence of the participatory words
The method of slot position is used for removing the entity in the sentence, and the left virtual word sequence is used as the target word to carry out frame recognition, so that the result only uses half of information, and therefore, the frame and frame elements of the sentence cannot be recognized.
For sentences with the works such as ' dam 3 well depth ' what is ' can be obtained by removing the entity words ' dam 3 ', ' well depth ' and reserving the slot position positions ', what is ' is, the frame of the sentence can be identified through the target word, but for sentences without works such as ' dam 3 well depth ', the works cannot be identified by the works sequence method.
(4) Parsing of questions cannot automatically obtain forms of answers
Because the question and the answer are presented in pairs, the question and the answer are different, so that the consistency of the words, the language and the semantics of the question and the answer is maintained. However, if the question is independently processed without considering the answer, a smooth answer form conforming to the scene and the semantics cannot be obtained.
Disclosure of Invention
The invention aims to provide a question and answer intention knowledge base construction method based on a question frame, which can solve the problems that in the prior art, frame elements are difficult to identify and question analysis answer forms cannot be automatically obtained.
In order to achieve the above object, the present invention provides the following technical solutions:
A question and answer intention knowledge base construction system based on a question framework, comprising: the data layer comprises a question corpus, a frame element dictionary and a question and answer intention knowledge base; the method is used for storing files, reading and writing files and modifying files;
the processing layer comprises a frame element processing module and a question and answer rewriting module and is used for rewriting sentences;
and the application layer comprises a question analysis module and is used for outputting candidate target word strings formed by rewriting sentences.
Based on the technical scheme, the invention can also be improved as follows:
Further, the question corpus comprises sequence numbers, question sources and questions, and the questions are used for recording relevant information of the questions.
Further, the format of the frame element dictionary comprises the name of the frame and the code number of the frame element; the framework element dictionary comprises question analysis, wherein the question analysis comprises a first layer and a second layer, the first layer is used for sequence analysis, and the second layer is used for implication relation and hierarchical structure analysis.
Further, the question-answering intention knowledge base comprises a question target word string and a question-answering intention analysis, wherein the question-answering intention analysis comprises a first part and a second part, the first part is a name of a frame, and the second part is an answer template.
Further, the frame element processing module is used for searching out word strings from the frame element dictionary.
Further, the rewrite module is used for replacing the word strings in the sentences to finish the rewrite of the sentences, and each rewritten sentence is added into the rewritten sentence set as a new original sentence to be accumulated until all the frame element character strings are used, so as to obtain a rewritten sentence set.
Further, the question analysis module is used for establishing a read-in question list, and outputting the frame target word strings formed by the rewritten sentences in a reverse ordering mode according to the word string length.
A method for constructing a question and answer intention knowledge base based on a question frame specifically comprises the following steps:
s101, constructing a sentence frame element dictionary according to the frame element dictionary and the question file;
s102, circulating the sentence frame element dictionary;
s103, circulating the existing sentence target word string set to form a new candidate target word string set, and reserving sentences in the new candidate target word string set;
s104, replacing corresponding words in the target word strings with the sentence frame element dictionary, and updating the candidate target word string set;
S105, sorting according to the lengths of the candidate target word strings, and outputting the candidate target word strings.
Further, constructing the sentence frame element dictionary specifically includes: and searching each sentence in the question file, and collecting the sentences in the frame element dictionary to form a sentence frame element dictionary when the words in the frame element dictionary appear in the sentences.
The invention has the following advantages:
According to the question and answer intention knowledge base construction system and method based on the question frame, information of all words and word sequences in the question is adopted to the greatest extent, the semantics of the target word strings of the question are reserved to the greatest extent, word-level object ambiguity can be effectively eliminated, recognition of the frame name of the question and analysis of frame elements and generation of answer sentences can be realized through the target word strings of the question, and analysis of the question and answer intention in the question and answer system is solved; the method solves the problems that in the prior art, the frame elements are difficult to identify and the answer sentence form of question analysis cannot be obtained automatically.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a knowledge base construction system for question and answer purposes in an embodiment of the invention;
FIG. 2 is a flowchart of a method for constructing a knowledge base of question and answer intents in an embodiment of the invention;
FIG. 3 is a schematic diagram of the definition of the frame element and the encoding rule of the question and answer frame name in the embodiment of the invention;
FIG. 4 is a schematic diagram of a format of a corpus of questions in an embodiment of the present invention;
FIG. 5 is a diagram of a framework element dictionary format in an embodiment of the present invention;
Fig. 6 is a schematic diagram of a knowledge base format of a question and answer chart in an embodiment of the invention.
Reference numerals illustrate:
The system comprises a data layer 10, a question corpus 101, a frame element dictionary 102, a question and answer intention knowledge base 103, a processing layer 20, a frame element processing module 201, a question and answer rewrite module 202, an application layer 30 and a question analysis module 301.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the present invention provides a question and answer intention knowledge base construction system based on a question framework, comprising:
a data layer 10 including a corpus of questions 101, a dictionary of frame elements 102, and a knowledge base of questions and answers 103; the method is used for storing files, reading and writing files and modifying files;
The processing layer 20 comprises a frame element processing module 201 and a question and answer sentence rewriting module 202, and is used for rewriting sentences;
The application layer 30 includes a question analysis module 301 for outputting candidate target word strings formed by rewritten sentences.
Sentence intent (sentence frame) is the meaning of sentences in the real world, which is a semantic meaning, and a method of frame semantics (FrameNet) is generally adopted, the name and frame elements of a frame are determined according to the scene where the frame is located, and the target words of the frame are defined according to predicates or verbs in the sentences.
For example, a frame named "talk and communicate" is defined in a social scenario, and generally has frame elements such as "sender", "receiver", "information", "medium", etc., and verbs included in sentences such as "say", "talk", "command", "tell", "discuss", "remind", "ask", "promise", "warn", "threat", etc. are all target words of the frame.
For a specific sentence, the frame to which the sentence belongs is determined by identifying the target word. The target words such as "Zhang Sanzhu Liqu airport where", "tell" indicate that the sentence belongs to the "talk-around interaction" frame, and "Zhang Sanzhu", "Liqu", "airport where" etc. are frame elements of the frame.
The entity words in the question sentence are replaced by the frame elements to form a complete word string combining virtual and real, so that the information of all words in the sentence is utilized to the maximum extent, and the complete sentence frame target word string is formed.
The specific operation is that firstly, the whole question-answer (including question and answer) frame and the question-answer frame element codes (such as frame number F111, frame element code T, time, O object and P parameter) are determined according to the question.
Secondly, constructing a frame element dictionary 102 according to the frames and the frame element codes of sentences; then, the corresponding entity words in the original question and answer are replaced by the frame element codes, and the question and answer are rewritten (for example, "how much" is rewritten to "how much the TOP is the F111# TOP is the Q" in month 3 in 2020).
Defining the rewritten question as a target word under the selected frame for identifying the frame, and forming a question-answer frame corresponding to the sentence by taking the rewritten answer as a question-answer template and the question; and putting the question-answering frameworks of all the questions together to form the whole question-answering knowledge base.
Further, as shown in fig. 4, the corpus of questions 101 includes a sequence number, a source of the questions, and questions for recording related information of the questions.
The method is used for recording question related information, and the information can be expanded, such as adding information of regions, questioners and the like, so as to prepare for more accurate questions and answers in the future.
Further, as shown in fig. 5, the format of the frame element dictionary 102 includes the frame name and the frame element code; the framework element dictionary 102 includes question parsing including a first layer for sequence parsing and a second layer for implication relationship and hierarchical parsing in consideration of granularity of time in chinese natural language and implication relationship of natural language such as "how much oil is produced". The definition of the frame names and the frame elements of the questions and answers are shown in fig. 2, wherein the questions and answers define TOPVM elements, and the answers define TOPVMQ and other 6 elements.
Further, as shown in the question-answer diagram knowledge base format of fig. 6, the question-answer knowledge base 103 includes a question target word string and a question-answer intention parse including a first portion and a second portion, where the question-answer intention parse includes a first portion and a second portion separated by "@ @" where the first portion is a frame name and the second portion is a question template.
Further, the frame element processing module 201 is configured to find a word string from the frame element dictionary 102.
Further, the rewrite module is used for replacing the word strings in the sentences to finish the rewrite of the sentences, and each rewritten sentence is added into the rewritten sentence set as a new original sentence to be accumulated until all the frame element character strings are used, so as to obtain a rewritten sentence set.
The target word string set of the original question sentence after being rewritten not only comprises a sentence pattern constructed by the virtual word part of the original sentence, but also comprises a frame or a slot constructed by the real word part, so that the method utilizes the information in the sentence and is the most complete construction mode of the target word of the sentence subframe.
Further, the question analysis module 301 is configured to establish a read-in question list, and output a frame target word string formed by rewriting the question in a reverse order according to the word string length. For people to select and verify proper frame target word strings. For a simple question, "what the gas production of 401-1 well is", because the number of dictionaries is large, typically on the order of 100 tens of thousands, 163 possible frame target word strings will be output, with only "what the OP is" being the correct question frame target word string. The more complex the question, the more frame elements are included, and the greater the number of frame target word strings that are output.
A method for constructing a question and answer intention knowledge base based on a question frame specifically comprises the following steps:
s101, constructing a sentence frame element dictionary 102;
In this step, a sentence frame element dictionary 102 is constructed from the frame element dictionary 102 and the question file; the frame element dictionary 102 is opened and the entire dictionary is read into memory to speed up processing. Opening an input question file to process each sentence in the question file; sentences in the question file are read in terms of periods. The frame elements corresponding to each question in the sentence frame element dictionary 102dic are constructed differently, and therefore, each sentence needs to be searched separately.
Whenever a word in the frame element dictionary 102 appears in a sentence, it is collected in the sentence frame element dictionary 102. This sentence-frame element dictionary 102 is large in number and may have complex inclusion relationships, such as "1" may be month data or may be physical well number, which requires full revenue into the sentence-frame element dictionary 102.
S102, cycling the sentence frame element dictionary 102;
in this step, the sentence frame element dictionary 102 is cycled; cycling according to the sentence frame element dictionary 102 dic; a loop of the entire element dictionary is constituted. Each occurrence in the dictionary should be exhausted, and the possibility of each sentence rewriting construction candidate target word string is checked.
S103, circulating the existing sentence target word string set;
In the step, circulating the existing sentence target word string set to form a new candidate target word string set, and reserving sentences in the new candidate target word string set; cycling the existing sentence target word string set; and updating the single element dictionary by the target word string set. The existing set of sentence target word strings is a variable, increasing set because the number of candidate target word string sets will increase every time a sentence replaces a word in an element dictionary.
Here, all the target word strings are updated once. Retaining sentences in the new candidate target word string set; the original sentence is always kept in the target candidate word string set, and expansion of the candidate word string set is realized. And the automatic duplication removal of sentences is realized by adopting a new collection mode.
S104, updating the candidate target word string set;
In this step, the sentence frame element dictionary 102 is used to replace the corresponding word in the target word string, and the candidate target word string set is updated; replacing corresponding words in the target word string with the sentence-frame element dictionary 102 dic; sentences with new word substitutions are also added to the target word string set. It should be noted that if there are several identical element words in the sentence, only one element word can be replaced at a time, and the rest element words to be replaced later can be replaced.
The processing of the next element word is formed together with the step S102, and the key point is that the target word string set is an updated new set, and all non-repeated candidate target word strings processed from the original sentence to each dictionary in the middle are accumulated;
s105, outputting candidate target word strings;
In the step, the candidate target word strings are output according to the length sequence of the candidate target word strings.
Further, constructing the sentence frame element dictionary 102 specifically includes: each sentence in the question file is searched, and when a word in the frame element dictionary 102 appears in the sentence, the sentence is collected in the frame element dictionary 102 to form a sentence frame element dictionary 102.
Sequencing according to the length of the candidate target word strings; the candidate target word strings are ordered from small to large in length because, in general, the longer word semantics are more definite the greater the number of words, and therefore, after substitution, the shorter the entire target word string is, the more likely it is that the correct target word string is required. Such ordering may reduce the time for a person to find the correct target word string. Outputting all candidate target word string files; and constructing a target word string sequence for each question, and then recording the target word string sequence in a file for outputting for manual inspection.
The construction method of the question and answer intention knowledge base 103 based on the question frame comprises the following steps:
When in use, an operator constructs a sentence frame element dictionary 102 according to the frame element dictionary 102 and the question file; cycling the sentence frame element dictionary 102; cycling the existing sentence target word string set to form a new candidate target word string set, and reserving sentences in the new candidate target word string set; replacing corresponding words in the target word strings with the sentence frame element dictionary 102 to update the candidate target word string set; and sequencing according to the lengths of the candidate target word strings, and outputting the candidate target word strings.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the stated features. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise. Furthermore, the terms "mounted," "connected," "coupled," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (8)
1. A question and answer intention knowledge base construction system based on a question framework, comprising:
The data layer comprises a question corpus, a frame element dictionary and a question and answer intention knowledge base; the method is used for storing files, reading and writing files and modifying files;
The format of the frame element dictionary comprises the name of the frame and the code number of the frame element; the frame element dictionary comprises question analysis, wherein the question analysis comprises a first layer and a second layer, the first layer is used for sequence analysis, and the second layer is used for implication relation and hierarchical structure analysis;
the processing layer comprises a frame element processing module and a question and answer rewriting module and is used for rewriting sentences;
and the application layer comprises a question analysis module and is used for outputting candidate target word strings formed by rewriting sentences.
2. The question-and-answer knowledge base construction system based on a question framework according to claim 1, wherein the question corpus comprises sequence numbers, question sources and questions for recording relevant information of the questions.
3. The question and answer knowledge base construction system based on a question framework according to claim 1, wherein the question and answer knowledge base comprises a question target word string and a question and answer analysis, the question and answer analysis comprises a first part and a second part, the first part is a name of the framework, and the second part is a question template.
4. The question and answer knowledge base construction system based on a question framework according to claim 1, wherein the framework element processing module is configured to find a word string from the framework element dictionary.
5. The system for constructing a knowledge base of question and answer based on a question and sentence framework according to claim 4, wherein the rewrite module is configured to replace a word string in the sentence with a character to complete the rewriting of the sentence, and each rewritten sentence is added as a new original sentence to a rewritten sentence set for accumulation until all the framework element character strings are used, so as to obtain a rewritten sentence set.
6. The question-answering intention knowledge base construction system based on a question framework according to claim 5, wherein the question analysis module is configured to build a read-in question list, and output a frame target word string formed by the rewritten sentences in a reverse order according to a word string length.
7. A method for constructing a question and answer intention knowledge base based on a question frame is characterized by comprising the following steps:
s101, constructing a sentence frame element dictionary according to the frame element dictionary and the question file;
s102, circulating the sentence frame element dictionary;
s103, circulating the existing sentence target word string set to form a new candidate target word string set, and reserving sentences in the new candidate target word string set;
s104, replacing corresponding words in the target word strings with the sentence frame element dictionary, and updating the candidate target word string set;
S105, sorting according to the lengths of the candidate target word strings, and outputting the candidate target word strings.
8. The method for constructing a knowledge base of question and answer intentions based on a frame of questions as claimed in claim 7, wherein constructing a dictionary of sentence frame elements comprises: and searching each sentence in the question file, and collecting the sentences in the frame element dictionary to form a sentence frame element dictionary when the words in the frame element dictionary appear in the sentences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040888.1A CN112650846B (en) | 2021-01-13 | 2021-01-13 | Question and answer intention knowledge base construction system and method based on question frame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040888.1A CN112650846B (en) | 2021-01-13 | 2021-01-13 | Question and answer intention knowledge base construction system and method based on question frame |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112650846A CN112650846A (en) | 2021-04-13 |
| CN112650846B true CN112650846B (en) | 2024-08-23 |
Family
ID=75367975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110040888.1A Active CN112650846B (en) | 2021-01-13 | 2021-01-13 | Question and answer intention knowledge base construction system and method based on question frame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112650846B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114626384A (en) * | 2022-03-01 | 2022-06-14 | 京东科技信息技术有限公司 | Dialogue processing method, question rewriting model training method and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428483A (en) * | 2020-03-31 | 2020-07-17 | 华为技术有限公司 | Voice interaction method and device and terminal equipment |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097573B (en) * | 2006-06-28 | 2010-06-09 | 腾讯科技（深圳）有限公司 | Automatically request-answering system and method |
| CN101470700A (en) * | 2007-12-28 | 2009-07-01 | 日电（中国）有限公司 | Text template generator, text generation equipment, text checking equipment and method thereof |
| JP5829000B2 (en) * | 2008-08-20 | 2015-12-09 | 株式会社ユニバーサルエンターテインメント | Conversation scenario editing device |
| CN103020040A (en) * | 2011-09-27 | 2013-04-03 | 富士通株式会社 | Rewriting processing method and equipment of source languages, and machine translation system |
| JP5439606B1 (en) * | 2012-09-07 | 2014-03-12 | 株式会社東芝 | Structured document management apparatus, method and program |
| US9436288B2 (en) * | 2013-05-17 | 2016-09-06 | Leap Motion, Inc. | Cursor mode switching |
| CN104715168B (en) * | 2015-02-13 | 2018-10-09 | 陈佳阳 | A kind of file security management and control based on digital finger-print and the method and system traced to the source |
| JP6767224B2 (en) * | 2016-09-29 | 2020-10-14 | 株式会社東芝 | Communication devices, communication methods, and communication programs |
| JP6652045B2 (en) * | 2016-12-26 | 2020-02-19 | トヨタ自動車株式会社 | Self-driving vehicle |
| CN109002432B (en) * | 2017-06-07 | 2022-01-04 | 北京京东尚科信息技术有限公司 | Synonym mining method and device, computer readable medium and electronic equipment |
| CN107748757B (en) * | 2017-09-21 | 2021-05-07 | 北京航空航天大学 | Question-answering method based on knowledge graph |
| CN108073708A (en) * | 2017-12-20 | 2018-05-25 | 北京百度网讯科技有限公司 | Information output method and device |
| CN109408627B (en) * | 2018-11-15 | 2021-03-02 | 众安信息技术服务有限公司 | Question-answering method and system fusing convolutional neural network and cyclic neural network |
| CN110765277B (en) * | 2019-10-22 | 2023-06-09 | 河海大学常州校区 | Knowledge-graph-based mobile terminal online equipment fault diagnosis method |
| CN111949774A (en) * | 2020-07-08 | 2020-11-17 | 深圳鹏锐信息技术股份有限公司 | Intelligent question answering method and system |
| CN111930906A (en) * | 2020-07-29 | 2020-11-13 | 北京北大软件工程股份有限公司 | Knowledge graph question-answering method and device based on semantic block |
| CN112069298B (en) * | 2020-07-31 | 2024-06-14 | 杭州远传新业科技股份有限公司 | Man-machine interaction method, device and medium based on semantic web and intention recognition |
| CN111708874B (en) * | 2020-08-24 | 2020-11-13 | 湖南大学 | Man-machine interaction question-answering method and system based on intelligent complex intention recognition |
| CN112035610B (en) * | 2020-08-28 | 2023-04-07 | 康键信息技术（深圳）有限公司 | Medical field question and answer pair generation method and device, computer equipment and medium |
-
2021
- 2021-01-13 CN CN202110040888.1A patent/CN112650846B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428483A (en) * | 2020-03-31 | 2020-07-17 | 华为技术有限公司 | Voice interaction method and device and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112650846A (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11151179B2 (en) | Method, apparatus and electronic device for determining knowledge sample data set | |
| US5559693A (en) | Method and apparatus for efficient morphological text analysis using a high-level language for compact specification of inflectional paradigms | |
| US7620538B2 (en) | Constructing a translation lexicon from comparable, non-parallel corpora | |
| CN117076653B (en) | Knowledge base question-answering method based on thinking chain and visual lifting context learning | |
| US9047275B2 (en) | Methods and systems for alignment of parallel text corpora | |
| CN106537370A (en) | Method and system for robust tagging of named entities in the presence of source or translation errors | |
| Neme et al. | Pattern-and-root inflectional morphology: the Arabic broken plural | |
| JP2005535007A (en) | Synthesizing method of self-learning system for knowledge extraction for document retrieval system | |
| KR100835706B1 (en) | System and method for korean morphological analysis for automatic indexing | |
| CN107656921B (en) | Short text dependency analysis method based on deep learning | |
| Cahill et al. | Wide-coverage deep statistical parsing using automatic dependency structure annotation | |
| CN112395425A (en) | Data processing method and device, computer equipment and readable storage medium | |
| CN113535977A (en) | Knowledge graph fusion method, device and equipment | |
| CN112650846B (en) | Question and answer intention knowledge base construction system and method based on question frame | |
| CN115390806A (en) | Software design mode recommendation method based on bimodal joint modeling | |
| Schick | Transition-Based Generation from Abstract Meaning Representations | |
| Perez-Beltrachini et al. | Semantic parsing for conversational question answering over knowledge graphs | |
| JP2001318792A (en) | Intrinsic expression extraction rule generation system and method, recording medium recorded with processing program therefor, and intrinsic expression extraction device | |
| CN111782773B (en) | Text matching method and device based on cascade mode | |
| CN115831117A (en) | Entity identification method, entity identification device, computer equipment and storage medium | |
| CN115906878A (en) | Machine translation method based on prompt | |
| CN115033706A (en) | Method for automatically complementing and updating knowledge graph | |
| CN112784019A (en) | Classroom note-taking system based on knowledge graph | |
| CN114021589A (en) | Sample generation method and device, computer equipment and storage medium | |
| RU2785207C1 (en) | Method and system for automatic search and correction of errors in texts in natural language |
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 |