CN105701253A - Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method - Google Patents

Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method Download PDF

Info

Publication number
CN105701253A
CN105701253A CN201610125710.6A CN201610125710A CN105701253A CN 105701253 A CN105701253 A CN 105701253A CN 201610125710 A CN201610125710 A CN 201610125710A CN 105701253 A CN105701253 A CN 105701253A
Authority
CN
China
Prior art keywords
question sentence
knowledge base
fact
template
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.)
Granted
Application number
CN201610125710.6A
Other languages
Chinese (zh)
Other versions
CN105701253B (en
Inventor
胡伟
姜成樾
程龚
瞿裕忠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University
Original Assignee
Nanjing University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University filed Critical Nanjing University
Priority to CN201610125710.6A priority Critical patent/CN105701253B/en
Publication of CN105701253A publication Critical patent/CN105701253A/en
Application granted granted Critical
Publication of CN105701253B publication Critical patent/CN105701253B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F16/3331—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
    • 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
    • G06F16/3332—Query translation
    • G06F16/3335—Syntactic pre-processing, e.g. stopword elimination, stemming
    • 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
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Machine Translation (AREA)

Abstract

The invention discloses a Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method. The method includes the following steps that Chinese natural language processing is performed on a fact type question input by a user, word segmentation, part-of-speech tagging and identification and expanding of a named entity are achieved, and a semantic dependency tree is generated; a generalization template and a semantic analysis technology are used for acquiring time, space, a fact entity, a fact object and the like in an interrogative sentence, then semantic processing is performed, composition element attributes relevant to all events in the interrogative sentence and values of the attributes are extracted, a plurality of 'attribute-value' pairs are generated, to-be-answered elements are substituted by interrogatives, and a complex fact triple set is formed; after a triple where a to-be-answered part is located is combined with other relevant fact triple sets to form knowledge base query with conditional constraints, and query matching based on similarity calculation is performed in a knowledge base, a result is extracted from the knowledge base, and a final answer is obtained. Fast and accurate query response to the knowledge base is achieved.

Description

The knowledge base automatic question-answering method of Chinese natural language question sentence semantization
Technical field
The present invention relates to semantic net, natural language processing and automatic question answering technology, particularly relate to the knowledge base automatic question-answering method of a kind of Chinese natural language question sentence semantization, the specifically knowledge base automatic question-answering method of a kind of Chinese natural language question sentence semantization based on template extraction, particularly a kind of convert KnowledgeBase-query to and realizes the knowledge base automatic question-answering method of fact-oriented type problem by Chinese natural language question sentence carries out the semantization of template extraction。
Background technology
Semantic net (SemanticWeb) is an important development direction of WWW, provides the foundation for the representation of knowledge on WWW, reasoning, exchange and multiplexing。Semantic net uses one group " attribute value " to describe entity therein (entity), and single " attribute value " is to being expressed as < pi,vi>, wherein piRepresent certain attribute, viRepresent piCertain value。Entity can be described as one or more this kind of value to set。Such as WWW inventor Mr. TimBerners-Lee, its name is represented as<name, " TimBerners-Lee ">in the DBpedia of semantic web data source。Generally, a semantic net entity description comprises tens of or even up to a hundred such " attribute value ", and an attribute can also have multiple different value。Along with semantic net is fast-developing, semantic network technology has had research in various degree and application in each different field。
Natural language processing (naturallanguageprocessing) is a subject of the language issues that research people interacts with a computer。Process natural language it is crucial that to allow computer " understanding " natural language, the key technology of natural language processing includes the participle of nature statement, part-of-speech tagging, name Entity recognition, reference resolution, syntax dependency parsing etc.。
Question and answer technology (questionanswering), is a kind of advanced form of information retrieval technique, and it can answer the natural language problem of user with accurate, succinct natural language。Automatically request-answering system can automatically analyze problem and provide corresponding candidate answers, and traditional automatically request-answering system is mainly by module compositions such as case study, information retrieval and answer generations。
Traditional automatic question answering is mainly what text-oriented set carried out, including the key word in problem analysis, key word is submitted to search engine, retrieves relevant documentation, obtain and return front some documents that in result, certainty factor is the highest, more therefrom generate answer from text library。But it is as the development of semantic network technology and popularizes gradually, the structural knowledge storehouse that the information tissue degree such as knowledge mapping (knowledgegraph), link data (linkeddata) are higher is risen, such as DBpedia and Freebase so that new-type realize automatic question answering based on structural knowledge storehouse and be possibly realized。
The collection of document of considerable scale, after resolving through semanteme, adopts structurized representation of knowledge form (the common tlv triple structure being expressed as " entity attribute value "), defines the knowledge base comprising a large amount of tlv triple。The basis of this knowledge base carries out automatic question answering, more highly efficient, accurate than traditional text based automatic question answering。If user can use inquiry that knowledge base is putd question to, answer precisely can be obtained undoubtedly rapidly。But when practice automatic question answering technology, major part user can not realize the question formulation of this " specialty ", and often only the form of Human Natural Language can be used to put question to, and therefore the knowledge base question and answer based on natural language question sentence have important value。In the automatic question answering process in knowledge based storehouse, after user inputs Chinese natural language question sentence, question sentence is only taked simple process to obtain key word by traditional method, and the query structure degree of generation is not high, it is impossible to realize the inquiry to knowledge base data precise and high efficiency。
Summary of the invention
The present invention is towards the knowledge base (hereinafter referred to as " knowledge base ") of tlv triple structure, propose a kind of Chinese natural language question sentence by user being inputted and carry out the semantization based on template extraction, convert Chinese natural language question sentence to structuralized query, it is achieved the automatic question-answering method of type problem of the fact that towards knowledge base。
True type problem can be divided into simple fact type problem and complexity fact type problem。Simple fact, is namely directly expressed as the form of single tlv triple in knowledge base, for instance " capital of France is Paris " is a simple fact, is expressed as<" France ", " capital ", " Paris ">in knowledge base。And complexity true usual include in natural statement time or point adverbial description, more include participant's main body or object and true relevant behavior act, such as " nineteen fifty; Alan schemes spirit and proposes turing test in Univ Manchester UK ", and for example " Nobel died in 1896 ", it has increasingly complex representation, similar blank node (blanknode) in knowledge base, being discussed further below, this type of complicated true statement comes across in gio signal class text more。The present invention is for complicated true type problem, but method is applied equally to simple fact type problem。
It is an object of the invention to: in the automatic question answering process of knowledge base, use semantic net and natural language processing technique that Chinese natural language question sentence is carried out structuring conversion, thus realizing the inquiry response fast and accurately to knowledge base。
The technical scheme is that user inputs a true type problem, inquire the part fact content therein (time that the such as inquiry fact is relevant, place or master, arbitrary content such as object), it is analyzed processing to question sentence first by natural language processing instrument, extract corresponding key word, re-use the Corpus--based Method extensive template that obtains of study and time that semantic analytic technique identifies in question sentence and space (including at least), the components such as true main body and true object (including at least), part to be answered replaces with interrogative, form complicated true triplet sets。Wait to answer the KnowledgeBase-query that part place tlv triple combines one SNNP constraint of other relevant fact tlv triple formation, the match query based on Similarity Measure is carried out in knowledge base, extract from the candidate result that similarity is the highest and wait to answer composition, obtain final result。
The knowledge base automatic question-answering method of Chinese natural language question sentence semantization comprises the following steps:
1. user inputs a true type problem, extracts the key word in question sentence by technology such as the participle of natural language processing, part-of-speech tagging, name Entity recognition and is extended based on common finger entity, and natural language question sentence is converted into the semantic dependent tree with mark；
2. obtain one group of question matching template based on fairly large statistical learning, including the node template of dependency tree, the structure canonical template (being likely to there is different structure canonical templates for different problem typess) of dependency tree and intermediate object program template, coupling by question sentence and template, realize all kinds of part of speech identification, question sentence trunk contents extraction, finally give the intermediate object program that can be used for structure inquiry triplet sets；
3. use typical space-time restriction class fact type question template, extract " time ", " place " true in question sentence, the component such as " true main body ", " true object ", " true behavior act ", realize the semantization to intermediate object program, and then generate multiple " entity attribute value " tuple。The complicated true triplet sets obtained is carried out KnowledgeBase-query, this set can be considered as a KnowledgeBase-query with other tlv triple constraints, in the reality query script to knowledge base, carry out the match query based on Similarity Measure, from similarity soprano, extract element value to be answered, replace interrogative and generate the final result that question sentence is asked。
The invention has the beneficial effects as follows: (1) defines the extensive template of one group of Corpus--based Method study, it is possible to suitable in parsing and the Match of elemental composition of Chinese natural language question sentence, mark sentence constituent to greatest extent。(2) semantic net and natural language processing technique is used to process true type Chinese natural language question sentence, the structuring semantic model of a clear logic is constructed for question sentence, more fine more concrete than the dependency tree content obtained after single natural language processing, it is easier to the understanding of machine and process。(3) based on the semantic model of template extraction and true type question sentence, obtain the KnowledgeBase-query of SNNP constraint, be easier to find answer accurately in knowledge base。
Accompanying drawing explanation
Fig. 1 is the disposed of in its entirety flow chart of the present invention；
Fig. 2 is the semantization model of the space-time restriction class fact type problem that the present invention defines。
Specific embodiment
The invention discloses the knowledge base automatic question-answering method of a kind of Chinese natural language question sentence semantization based on template extraction, comprise the following steps: first the fact that user inputs type problem is carried out Chinese natural language process, realize participle, part-of-speech tagging, name Entity recognition and extension, generative semantics dependency tree；Next the extensive template that Corpus--based Method study obtains is used to obtain the constituents such as the time in question sentence, space, true main body, true object with semantic analytic technique, then semantization process is carried out, extract component attribute and value thereof that in question sentence, all events are relevant, generate multiple " attribute value " right, element wherein to be answered replaces with interrogative, forms complicated true triplet sets；Finally, wait to answer the KnowledgeBase-query that part place tlv triple combines one SNNP constraint of other relevant fact tlv triple formation, in knowledge base, carry out the match query based on Similarity Measure, from knowledge base, extract result, obtain final result。
The entire flow of the present invention is as shown in Figure 1, including 3 parts: carry out Chinese natural language process according to the fact that user inputs type problem and realize keyword extraction and refer to that extension obtains semantic dependent tree altogether, semantic dependent tree is mated the part-of-speech tagging obtained specifically by the one group of template using predefined according to obtained dependency tree, trunk contents extraction and intermediate object program generate, knowledge base is carried out the match query based on Similarity Measure by the structuralized query finally using the semantic model structural belt constraint of space-time restriction class fact type problem, obtain Query Result and therefrom extract answer。
Specific embodiment is respectively described below:
1. carry out Chinese natural language process according to the fact that user inputs type problem realize keyword extraction and refer to that extension obtains semantic dependent tree altogether
The true type problem of a Chinese for input, first question sentence is carried out natural language processing, uses the Open-Source Tools bag FudanNLP of (NLPParser of such as Stanford Univ USA, Fudan University of China) that question sentence carries out participle, part-of-speech tagging, name Entity recognition and keyword abstraction。
In this process, in order to improve the accuracy rate of keyword abstraction, after sentence is disposed by Open-Source Tools, add some entity vocabularys and (include extracting from the special noun vocabulary of urtext database documents quotation marks content, take from the noun entry vocabulary of Chinese Wikipedia, ground noun list, people's noun list etc.) sentence carried out secondary verification, by originally increase income Chinese natural language handling implement Packet analyzing sentence time issuable cutting mistake (mainly some particular entity names of Open-Source Tools bag None-identified, long physical name, name, place name etc.) solve, improve the accuracy of participle as far as possible。
On above-mentioned participle basis, generate the semantic dependent tree of question sentence。
After extracting the key word of question sentence, it is contemplated that target text storehouse not necessarily comprises on all four word, extend so these key words being carried out corresponding finger altogether, mainly the synonym of key word/near synonym extension。Add and extract from the Chinese synonym table of Wikipedia, word woods, and the synonym of some manual sortings, near synonym vocabulary content。
2. use one group of template of predefined that dependency tree carries out coupling according to obtained semantic dependent tree and obtain more specifically part-of-speech tagging, trunk contents extraction and intermediate object program generation
The question matching template that predefined one group obtains based on fairly large statistical learning, form template is expressed including the node template of dependency tree, the structure canonical template of dependency tree and intermediate object program, by the question sentence coupling for template, realize all kinds of part-of-speech tagging identification, question sentence trunk contents extraction, finally give the structuring triplet sets that can be used for inquiry。
The matching process this group template applied on the dependency tree of question sentence is as follows:
(1) tree node template can parse the information (playing the effect of strengthening semantic tagger, specify interrogative pronoun, the name multiple statement composition such as substantive noun, predicate) of all interdependent nodes in question sentence。Define regular expression of all categories, be used for strengthening identification such as name, place name, time, physical name etc.。Further according to the mark of the name Entity recognition related in above-mentioned natural language processing process and extension vocabulary, mark dependency tree node classification in detail。
After combining above-mentioned (including the method such as regular expression and extension vocabulary) method that can be used for marking type of word of all categories, store structure and the content of each tree node by following tree node template:
Tree node template is used for accurately identifying the node meeting specified criteria, system carries out for problem after natural language processing, in the process that dependency tree interior joint is traveled through, realize the strengthening of each node content is marked, the type of the word content of each node is described in a kind of more detailed mode。
On this basis, the content of each node can be grouped under the classification of tree node template categorizedly, as the basis of second step tree construction canonical template matching。
(2) tree construction canonical template can resolve the node path coupling syntax tree path of question sentence dependency tree and obtains effective question sentence structure, extracts most useful content, is generally question sentence trunk content and crucial qualifier。In the template extraction flow process for true type problem, first step node template coupling can parse the noun content of time, place name, and true sentence structure trunk is not produced other influences by time, point adverbial, here select before carrying out dependency tree structure canonical template matching, make suitably to process, extract time, place noun, and remove preposition in time that may be present, point adverbial (as " ", " in " etc.)。
Specifically, the path according to the root node of syntax tree to leaf node, carry out the canonical template of definition tree structure, mate the path of syntax tree for canonical, extract useful field。Generally, the question sentence structure node of question and answer type of the same race has its general character, often with the time with preposition or point adverbial and Subjective and Objective behavior act in such as typical true type problem, resolves at node and has concordance in structure extraction。This feature allows tree node template have certain generalization ability, namely can by a tree node template matching one class general character node (namely some similar sentence pattern or similar theme question sentence have same or analogous tree construction canonical template)。
First tree is carried out path with root node for starting point, obtain a series of root node interdependent path to leaf node。These route matching use the form being similar to regular expression。The place being different from regular expression is in that, the ordinary item of regular expression is all character match, and the ordinary item of tree construction canonical template is all tree node template in system, but such a template just can mate the generation path with the different tree of same characteristic features node content。
Canonical template supports that canonical operation has: connect (" ab "), side by side (" a | b " or " [ab] "), Kleene repeats (greedy pattern " a* " and non-greedy pattern " a*？"), common repetition (greedy pattern " a+ " and non-greedy pattern " a+？"), optional (" a？") and location matches (starting position " ^ " and end position " $ ")。
The task of template is to identify specific minor structure and extract useful part from these minor structures, it is desirable to be able to extracts the node of the ad-hoc location of compatible portion, therefore supports to catch group based on the anonymity of bracket, catches group content and uses integer sequence number to conduct interviews。Therefore, matching result (can catch group by " modulus of regularity board name catches group # " easily, the subexpression matching content of regular expression, conveniently quote with numeral numbering, with " the order number consecutively that (" occurs in expression formula, general, 0 represents whole expression formula) access and obtain。
It addition, each tree can generate several paths, after all route matching complete, it is necessary to formed tree construction。Owing to different paths can share a part of node, when route matching result is integrated, therefore, to assure that the result of same node matching is also identical, and namely the corresponding node under Different matching path to be alignd。So the canonical template of each tree construction all adds " CONSTRAINTS " field, the node in order to retrain matching result between different paths aligns, and with as above, matching result is obtained by " modulus of regularity board name catches group # "。This field has only to express corresponding node matching content etc. or not etc., be therefore expressed as " (=modulus of regularity board name catches group # ...) " or " (！=modulus of regularity board name catches group # ...) "。
According to mentioned above, the problem of the identical problem solving classification or similar clause has same or analogous tree construction canonical template, therefore can define the corresponding extensive template being suitable in the process that practical problem resolves according to actual needs。Due to the complexity features that Chinese language is expressed, the number of this type of structure of transvers plate is still relatively many (be applicable to different Chinese and express the template of clause)。
Herein for typical space-time restriction class fact type problem, provide the formwork style of definition。One example flow of dependency tree matching template is as follows:
Example: " nineteen fifty, Alan schemes where spirit proposes turing test？"
According to natural language participle, the question sentence semantic dependent tree result tentatively obtained is:
" Alan schemes spirit ", " turing test " are the name entities through entity vocabulary identifying processing, assert that this character string is indivisible continuously。
It is noted here that, extract with solve time of not affecting of part or point adverbial part after, the root tree path that template obtains is " proposition → Alan schemes spirit ", " proposition → → where " and " proposition → turing test "。Template matching process afterwards is as follows:
Above, the template process of analysis of dependency tree node, the definition of canonical structure template and the tree node of a space-time restriction class fact type question sentence example, canonical structure it is。
For solving of space-time restriction class fact type problem, solving different true element, it is possible to other corresponding templates of like configurations, replace and solve interrogative pronoun, remaining basic format content of template is almost consistent。
(3) intermediate object program expresses the form template intermediate object program for obtaining after representing two above template extraction, is the question and answer solution of initial question sentence。Based on intermediate object program, then use the space-time restriction class fact type semantization model of predefined, generate corresponding entity relationship tlv triple, it is possible to for next step structuralized query。
Such as " what the capital of France is？"<" France ", " capital ", what>tlv triple that generates of the intermediate object program that obtains of question sentence be；" nineteen fifty, Alan schemes where spirit proposes turing test？" the triplet sets that generates of intermediate object program be Q:{<Q, " time ", " nineteen fifty ">,<Q, " place ", where>,<Q, " main body ", " Alan schemes spirit ">,<Q, " object ", " turing test ">,<" Alan schemes spirit ", " proposition ", " turing test ">}。
3. the semantization model using space-time restriction class fact type problem arranges intermediate object program, and knowledge base is carried out the match query based on Similarity Measure by the structuralized query of structural belt constraint, obtains Query Result and therefrom extracts answer
General, a complicated fact can parse multiple component, and most Expressive Features is true relevant time, place, true relevant main body, object, and the behavior act that main object is made。Time noun that space-time restriction class Fact Model obtains according to dependency tree node template, place noun, main body that canonical structure template obtains, object, action behavior (main body → object), accurately extract sentence to include producing the true { time, place, main body, object, behavior act } multiple components。If Partial Elements is without value, being expressed as sky (NULL), the tlv triple comprising null value can generate as required or not generate。
Use semantic network technology, semantic network technology empty node will be described as by the fact that represented by sentence。So-called blank node, representing cannot with the URI of the specific, concrete node identified。Under this situation, blank node represents a true statement (statement), and the concrete value of neither one own can describe it, but can expand its extension of description with the attributes such as time, place, Subjective and Objective and value thereof。
After each component extracting event statements and value thereof, with component for attribute, element value is concrete literal, respectively to each sentence generation multiple " entity attribute value " tlv triple。Specifically, tlv triple representation T=<s, p, o>, s represents that this tlv triple describes the subject of content, and p is predicate, and o is object。Subject centered by the event Q that event statements is expressed, then whole event (time, place, main body, object, behavior act) is namely represented by
Q:{Tt,Tl,Ts,To,Tact, Tt=<Q, time, tValue>, Tl=<Q, location, lValue>, Ts=<q,subject,sValue>, To=<Q, object, oValue>, Tact=<sValue, actValue, oValue>。
Content expressed by above-mentioned triplet sets can present by a kind of visual means, as shown in Figure 2 (note: when only true main body in true sentence, object merges with main body, and object value merges with main body value, and behavior act is formed from ring)。Distinguishingly, in a true statement, as without object situation, for instance " Nobel died in 1896 ", then being merged with main body by object, behavior act forms main body from ring。
The question sentence triplet sets obtained is carried out KnowledgeBase-query coupling。This set can be considered as a tlv triple with other tlv triple constraints and inquire about, and for question sentence fact triplet sets, the value of the tlv triple at answer element place to be solved replaces with interrogative。In the reality query script to knowledge base, the fact that ignore the literal of true Centroid Q and the fact in knowledge base description scheme the is similar literal similarity of Centroid, the unit that other literals are variate-value except Q in each tlv triple is carried out Similarity Measure (the i.e. time, place, main body, the fixed attribute names such as object must strictly be mated, attribute value then carries out Similarity Measure coupling), (synonym extension vocabulary is added with famous Jaro-Winkler character range formula, think that synonym similarity is 1) (Similarity-Weighted carrying out internal unit in the tlv triple of each first Similarity Measure comprising multiple literal variable again is average for tolerance, the unit's then Similarity Measure weight having n literal variable is 1/n, such as TactIn tlv triple, the Similarity Measure weight of each literal variable elements is 1/3) obtain the similarity of each group of fact component tlv triple, obtaining 5 Similarity value is { St,Sl,Ss,So,Sact}。
For question sentence triplet sets and each candidate's triplet sets, the similarity weight making each tlv triple is { Wt,Wl,Ws,Wo,Wact; here set for judging whether two true triplet sets express same facts; judgement effect produced by component therein is of equal value, therefore its 5 weight equivalent valuations is all 1/5=0.2, but also remains the probability adjusted flexibly according to practical situation。Then the final similarity S that true for question sentence and candidate answers sentence calculates and is:
S=WtSt+WlSl+WsSs+WoSo+WactSact.
Distinguishingly, it is possible to only time element or place element one and the situation of only true main body occur, therefore order again:
Wt+Wl=0.4, Ws+Wo=0.4。
And under this special case, the element similarity weight that value is empty is 0, and this fact tlv triple does not include Similarity Measure process in。
Based on above-mentioned calculating formula of similarity, calculate and obtain in question sentence fact triplet sets and knowledge base after the final similarity of each candidate's fact triplet sets, it is carried out descending, take triplet sets that Similarity value the maximum is most compliance problem (if there is the situation that multiple similarity is similar to very much with highest similarity, namely difference is less than 0.05, then think that they are all consistent with condition), therefrom extract and treat answer part, the interrogative in former question sentence tlv triple to be solved is replaced with corresponding content, it is the final result that can provide (owing to being based on Similarity Measure, therefore final result not necessarily complies fully with the actual fact, because knowledge base being likely not to have relevant information knowledge)。
The present invention is different from text answering method, but with the Chinese natural language semantization method based on template extraction, for true type problem, achieve the conversion to structuralized query of the Chinese natural language question sentence, realize again the automatic question answering in knowledge based storehouse in the way of based on the match query of Similarity Measure, it is possible to provide the answer extracting of to be solved part more more fine-grained than the whole sentence of text answers。

Claims (3)

1. the knowledge base automatic question-answering method of a Chinese natural language question sentence semantization, it is characterised in that comprise the following steps:
(1.1) for a true type Chinese natural language problem of input, extended by the keyword abstraction in problem and based on common finger entity, generative semantics dependency tree；
(1.2) semantic dependent tree obtained based on described step (1.1), the dependency tree node template of use predefined and Corpus--based Method learn the dependency tree structure canonical template obtained, extract the multiple true element and value thereof that comprise in question sentence, by intermediate object program template generation intermediate object program；
(1.3) based on described step (1.2) dependency tree obtains element value and the intermediate object program be correlated with via dependency tree node template and dependency tree structure canonical template extraction, with space-time restriction class Fact Model, described element value and intermediate object program semantization are generated triplet sets, form the KnowledgeBase-query based on Similarity Measure, from knowledge base, extract answer。
2. the knowledge base automatic question-answering method of Chinese natural language question sentence semantization according to claim 1, it is characterised in that described step (1.2) comprises the following steps:
(2.1) use the semantic dependent tree obtained based on described step (1.1), again strengthen coupling with dependency tree node template, mark out the part of speech classification that dependency tree node is concrete, generate markup information；
(2.2) markup information obtained based on described step (2.1), the trunk that dependency tree structure canonical template carries out question sentence is used to extract, the node path coupling syntax tree path resolving question sentence dependency tree obtains effective question sentence structure, extracts most useful question sentence trunk content and crucial qualifier；
(2.3) the question sentence trunk content obtained based on described step (2.2), use intermediate object program template generation intermediate object program, the content that intermediate object program represents is the solution that question sentence solves, and is the basis being subsequently generated the KnowledgeBase-query based on triplet sets。
3. the knowledge base automatic question-answering method of Chinese natural language question sentence semantization according to claim 2, it is characterised in that described step (1.3) comprises the following steps:
(3.1) define space-time restriction class Fact Model attribute be the time, place, main body, object, main object behavior act, the dependency tree node obtained by described step (2.1) and (2.2) and question sentence trunk content, determine the value of time, place, main body, object and behavior act that the question sentence fact is relevant, include waiting to answer element；
(3.2) value obtained is extracted based on described step (3.1), with SVO tlv triple<s, p, each factual aspect of o>Form generation, wherein treating that treating in the tlv triple of answer element is answered value interrogative and replaced, each question sentence can be expressed as a question sentence fact triplet sets；
(3.3) the question sentence fact triplet sets obtained based on described step (3.2), is organized into the KnowledgeBase-query of a Problem with Some Constrained Conditions；
(3.4) KnowledgeBase-query obtained based on affiliated step (3.3), subgraph match is carried out in knowledge base, candidate's triplet sets that description scheme each in knowledge base is similar is carried out the Similarity Measure of accurately coupling and the element property value of each element property name, element weights weighted average obtains the final similarity of each true triplet sets to the fact that again according to semantization model, by similarity height sequence, therefrom extract part to be answered, be final result。
CN201610125710.6A 2016-03-04 2016-03-04 The knowledge base automatic question-answering method of Chinese natural language question semanteme Active CN105701253B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610125710.6A CN105701253B (en) 2016-03-04 2016-03-04 The knowledge base automatic question-answering method of Chinese natural language question semanteme

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610125710.6A CN105701253B (en) 2016-03-04 2016-03-04 The knowledge base automatic question-answering method of Chinese natural language question semanteme

Publications (2)

Publication Number Publication Date
CN105701253A true CN105701253A (en) 2016-06-22
CN105701253B CN105701253B (en) 2019-03-26

Family

ID=56220835

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610125710.6A Active CN105701253B (en) 2016-03-04 2016-03-04 The knowledge base automatic question-answering method of Chinese natural language question semanteme

Country Status (1)

Country Link
CN (1) CN105701253B (en)

Cited By (97)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106295187A (en) * 2016-08-11 2017-01-04 中国科学院计算技术研究所 Construction of knowledge base method and system towards intelligent clinical auxiliary decision-making support system
CN106339366A (en) * 2016-08-08 2017-01-18 北京百度网讯科技有限公司 Method and device for requirement identification based on artificial intelligence (AI)
CN106503194A (en) * 2016-11-02 2017-03-15 大唐软件技术股份有限公司 Information getting method and device
CN106815745A (en) * 2016-12-30 2017-06-09 北京三快在线科技有限公司 Vegetable recommends method and system
CN106844335A (en) * 2016-12-21 2017-06-13 海航生态科技集团有限公司 Natural language processing method and device
CN106897273A (en) * 2017-04-12 2017-06-27 福州大学 A kind of network security dynamic early-warning method of knowledge based collection of illustrative plates
CN106919655A (en) * 2017-01-24 2017-07-04 网易（杭州）网络有限公司 A kind of answer provides method and apparatus
CN107169013A (en) * 2017-03-31 2017-09-15 北京三快在线科技有限公司 A kind of processing method and processing device of dish information
CN107193798A (en) * 2017-05-17 2017-09-22 南京大学 A kind of examination question understanding method in rule-based examination question class automatically request-answering system
CN107239450A (en) * 2017-06-02 2017-10-10 上海对岸信息科技有限公司 Natural language method is handled based on Interaction context
CN107239481A (en) * 2017-04-12 2017-10-10 北京大学 A kind of construction of knowledge base method towards multi-source network encyclopaedia
CN107247613A (en) * 2017-04-25 2017-10-13 北京航天飞行控制中心 Sentence analytic method and sentence resolver
CN107256226A (en) * 2017-04-28 2017-10-17 北京神州泰岳软件股份有限公司 The construction method and device of a kind of knowledge base
CN107423439A (en) * 2017-08-04 2017-12-01 逸途（北京）科技有限公司 A kind of Chinese charater problem mapping method based on LDA
CN107423437A (en) * 2017-08-04 2017-12-01 逸途（北京）科技有限公司 A kind of Question-Answering Model optimization method based on confrontation network intensified learning
CN107644011A (en) * 2016-07-20 2018-01-30 百度（美国）有限责任公司 System and method for the extraction of fine granularity medical bodies
CN107748757A (en) * 2017-09-21 2018-03-02 北京航空航天大学 A kind of answering method of knowledge based collection of illustrative plates
CN107818148A (en) * 2017-10-23 2018-03-20 南京南瑞集团公司 Self-service query and statistical analysis method based on natural language processing
CN107885844A (en) * 2017-11-10 2018-04-06 南京大学 Automatic question-answering method and system based on systematic searching
CN107895037A (en) * 2017-11-28 2018-04-10 北京百度网讯科技有限公司 A kind of question and answer data processing method, device, equipment and computer-readable medium
CN108052577A (en) * 2017-12-08 2018-05-18 北京百度网讯科技有限公司 A kind of generic text content mining method, apparatus, server and storage medium
CN108287822A (en) * 2018-01-23 2018-07-17 北京容联易通信息技术有限公司 A kind of Chinese Similar Problems generation System and method for
CN108376287A (en) * 2018-03-02 2018-08-07 复旦大学 Multi-valued attribute segmenting device based on CN-DBpedia and method
CN108446286A (en) * 2017-02-16 2018-08-24 阿里巴巴集团控股有限公司 A kind of generation method, device and the server of the answer of natural language question sentence
CN108491378A (en) * 2018-03-08 2018-09-04 国网福建省电力有限公司 Power information O＆M intelligent response system
CN108549710A (en) * 2018-04-20 2018-09-18 腾讯科技（深圳）有限公司 Intelligent answer method, apparatus, storage medium and equipment
CN108549694A (en) * 2018-04-16 2018-09-18 南京云问网络技术有限公司 The processing method of temporal information in a kind of text
CN108595696A (en) * 2018-05-09 2018-09-28 长沙学院 A kind of human-computer interaction intelligent answering method and system based on cloud platform
CN108733359A (en) * 2018-06-14 2018-11-02 北京航空航天大学 A kind of automatic generation method of software program
CN108984527A (en) * 2018-07-10 2018-12-11 广州极天信息技术股份有限公司 A kind of method for recognizing semantics and device based on concept
CN109344385A (en) * 2018-01-30 2019-02-15 深圳壹账通智能科技有限公司 Natural language processing method, apparatus, computer equipment and storage medium
CN109344236A (en) * 2018-09-07 2019-02-15 暨南大学 One kind being based on the problem of various features similarity calculating method
CN109408811A (en) * 2018-09-29 2019-03-01 联想(北京)有限公司 A kind of data processing method and server
CN109522418A (en) * 2018-11-08 2019-03-26 杭州费尔斯通科技有限公司 A kind of automanual knowledge mapping construction method
CN109613917A (en) * 2018-11-02 2019-04-12 广州城市职业学院 A kind of question and answer robot and its implementation
CN109684448A (en) * 2018-12-17 2019-04-26 北京北大软件工程股份有限公司 A kind of intelligent answer method
CN109684354A (en) * 2017-10-18 2019-04-26 北京国双科技有限公司 Data query method and apparatus
CN109710939A (en) * 2018-12-28 2019-05-03 北京百度网讯科技有限公司 Method and apparatus for determining theme
CN109753541A (en) * 2018-12-10 2019-05-14 北京明略软件系统有限公司 A kind of relational network construction method and device, computer readable storage medium
CN109766994A (en) * 2018-12-25 2019-05-17 华东师范大学 A kind of neural network framework of natural language inference
CN109902087A (en) * 2019-02-02 2019-06-18 上海奔影网络科技有限公司 For the data processing method and device of question and answer, server
WO2019114430A1 (en) * 2017-12-15 2019-06-20 王碧波 Natural language question understanding method and apparatus, and electronic device
CN109949637A (en) * 2019-03-13 2019-06-28 广东小天才科技有限公司 A kind of objective item purpose answers method and apparatus automatically
CN109977421A (en) * 2019-04-15 2019-07-05 南京邮电大学 A kind of Knowledge Base of Programming subjects answering system after class
CN109977370A (en) * 2019-03-19 2019-07-05 河海大学常州校区 It is a kind of based on the question and answer of document collection partition to method for auto constructing
CN110019687A (en) * 2019-04-11 2019-07-16 宁波深擎信息科技有限公司 A kind of more intention assessment systems, method, equipment and the medium of knowledge based map
CN110020015A (en) * 2017-12-29 2019-07-16 中国科学院声学研究所 A kind of conversational system answers generation method and system
CN110096580A (en) * 2019-04-24 2019-08-06 北京百度网讯科技有限公司 A kind of FAQ dialogue method, device and electronic equipment
CN110147436A (en) * 2019-03-18 2019-08-20 清华大学 A kind of mixing automatic question-answering method based on padagogical knowledge map and text
CN110321544A (en) * 2019-07-08 2019-10-11 北京百度网讯科技有限公司 Method and apparatus for generating information
CN110334179A (en) * 2019-05-22 2019-10-15 深圳追一科技有限公司 Question and answer processing method, device, computer equipment and storage medium
CN110347808A (en) * 2019-05-28 2019-10-18 成都美美臣科技有限公司 One e-commerce website intelligent robot customer service construction method
CN110349477A (en) * 2019-07-16 2019-10-18 湖南酷得网络科技有限公司 A kind of misprogrammed restorative procedure, system and server based on history learning behavior
CN110362662A (en) * 2018-04-09 2019-10-22 北京京东尚科信息技术有限公司 Data processing method, device and computer readable storage medium
WO2019205705A1 (en) * 2018-04-28 2019-10-31 厦门快商通信息技术有限公司 Semantic-framework-based human-machine conversation method and system
CN110427471A (en) * 2019-07-26 2019-11-08 四川长虹电器股份有限公司 A kind of natural language question-answering method and system of knowledge based map
CN110532358A (en) * 2019-07-05 2019-12-03 东南大学 A kind of template automatic generation method towards knowledge base question and answer
CN110532366A (en) * 2019-09-03 2019-12-03 出门问问(武汉)信息科技有限公司 A kind of pattern rule management method, language generation method, apparatus and storage equipment
CN110727780A (en) * 2019-10-17 2020-01-24 福建天晴数码有限公司 System and method for automatically expanding acquaintance text
CN110727782A (en) * 2019-10-22 2020-01-24 苏州思必驰信息科技有限公司 Question and answer corpus generation method and system
CN110851560A (en) * 2018-07-27 2020-02-28 杭州海康威视数字技术股份有限公司 Information retrieval method, device and equipment
CN110852110A (en) * 2018-07-25 2020-02-28 富士通株式会社 Target sentence extraction method, question generation method, and information processing apparatus
CN110852067A (en) * 2019-10-10 2020-02-28 杭州量之智能科技有限公司 Question analysis method for non-entity word dependency extraction based on SVM
CN110858100A (en) * 2018-08-22 2020-03-03 北京搜狗科技发展有限公司 Method and device for generating association candidate words
CN110990541A (en) * 2018-09-30 2020-04-10 北京国双科技有限公司 Method and device for realizing question answering
CN111125150A (en) * 2019-12-26 2020-05-08 成都航天科工大数据研究院有限公司 Industrial field question-answering system retrieval method
CN111159345A (en) * 2019-12-27 2020-05-15 中国矿业大学 Chinese knowledge base answer obtaining method and device
CN111210824A (en) * 2018-11-21 2020-05-29 深圳绿米联创科技有限公司 Voice information processing method and device, electronic equipment and storage medium
CN111241841A (en) * 2018-11-13 2020-06-05 第四范式（北京）技术有限公司 Semantic analysis method and device, computing equipment and readable medium
CN111339269A (en) * 2020-02-20 2020-06-26 来康科技有限责任公司 Knowledge graph question-answer training and application service system with automatically generated template
CN111382256A (en) * 2020-03-20 2020-07-07 北京百度网讯科技有限公司 Information recommendation method and device
CN111400458A (en) * 2018-12-27 2020-07-10 上海智臻智能网络科技股份有限公司 Automatic generalization method and device
CN111459973A (en) * 2020-06-16 2020-07-28 四川大学 Case type retrieval method and system based on case situation triple information
CN111553160A (en) * 2020-04-24 2020-08-18 北京北大软件工程股份有限公司 Method and system for obtaining answers to question sentences in legal field
WO2020168702A1 (en) * 2019-02-21 2020-08-27 扬州大学 Template-based automatic software defect question and answer method
CN111625623A (en) * 2020-04-29 2020-09-04 奇安信科技集团股份有限公司 Text theme extraction method, text theme extraction device, computer equipment, medium and program product
CN111651569A (en) * 2020-04-24 2020-09-11 中国电力科学研究院有限公司 Knowledge base question-answering method and system in electric power field
CN111708800A (en) * 2020-05-27 2020-09-25 北京百度网讯科技有限公司 Query method and device and electronic equipment
CN111709250A (en) * 2020-06-11 2020-09-25 北京百度网讯科技有限公司 Method, apparatus, electronic device, and storage medium for information processing
CN111858866A (en) * 2019-04-30 2020-10-30 广东小天才科技有限公司 Semantic analysis method and device based on triples
CN111886601A (en) * 2019-03-01 2020-11-03 卡德乐人工智能私人有限公司 System and method for adaptive question answering
WO2020221142A1 (en) * 2019-04-28 2020-11-05 华为技术有限公司 Picture book-based question and answer interaction method and electronic device
CN111949781A (en) * 2020-08-06 2020-11-17 贝壳技术有限公司 Intelligent interaction method and device based on natural sentence syntactic analysis
CN112182230A (en) * 2020-11-27 2021-01-05 北京健康有益科技有限公司 Text data classification method and device based on deep learning
CN112256847A (en) * 2020-09-30 2021-01-22 昆明理工大学 Knowledge base question-answering method integrating fact texts
CN112287080A (en) * 2020-10-23 2021-01-29 平安科技（深圳）有限公司 Question sentence rewriting method and device, computer equipment and storage medium
CN112347121A (en) * 2020-11-02 2021-02-09 中科曙光南京研究院有限公司 Configurable method and system for converting natural language into sql
CN112380848A (en) * 2020-11-19 2021-02-19 平安科技（深圳）有限公司 Text generation method, device, equipment and storage medium
CN112417170A (en) * 2020-11-23 2021-02-26 南京大学 Relation linking method for incomplete knowledge graph
CN112733547A (en) * 2020-12-28 2021-04-30 北京计算机技术及应用研究所 Chinese question semantic understanding method by utilizing semantic dependency analysis
CN112906559A (en) * 2021-02-10 2021-06-04 网易有道信息技术（北京）有限公司 Machine-implemented method for correcting formulas and related product
WO2021135103A1 (en) * 2020-05-29 2021-07-08 平安科技（深圳）有限公司 Method and apparatus for semantic analysis, computer device, and storage medium
CN113590782A (en) * 2021-07-28 2021-11-02 北京百度网讯科技有限公司 Training method, reasoning method and device of reasoning model
CN113761940A (en) * 2021-09-09 2021-12-07 杭州隆埠科技有限公司 News subject judgment method, equipment and computer readable medium
CN114357123A (en) * 2022-03-18 2022-04-15 北京创新乐知网络技术有限公司 Data matching method, device and equipment based on hierarchical structure and storage medium
CN115080742A (en) * 2022-06-24 2022-09-20 北京百度网讯科技有限公司 Text information extraction method, device, equipment, storage medium and program product
CN117332097A (en) * 2023-11-30 2024-01-02 北京大数据先进技术研究院 Knowledge question-answering method, device and product based on space-time semantic constraint

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001082125A1 (en) * 2000-04-25 2001-11-01 Invention Machine Corporation, Inc. Creation of tree-based and customized industry-oriented knowledge base
CN101373532A (en) * 2008-07-10 2009-02-25 昆明理工大学 FAQ Chinese request-answering system implementing method in tourism field
CN101799802A (en) * 2009-02-05 2010-08-11 日电（中国）有限公司 Method and system for extracting entity relationship by using structural information

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001082125A1 (en) * 2000-04-25 2001-11-01 Invention Machine Corporation, Inc. Creation of tree-based and customized industry-oriented knowledge base
CN101373532A (en) * 2008-07-10 2009-02-25 昆明理工大学 FAQ Chinese request-answering system implementing method in tourism field
CN101799802A (en) * 2009-02-05 2010-08-11 日电（中国）有限公司 Method and system for extracting entity relationship by using structural information

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
M SHUAIB QURESHI.ETC: "Proposed architectural model for optimal transformation of decision table and decision tree into knowledge base", 《INDIAN JOURNAL OF SCIENCE & TECHNOLOGY》 *
李静静: "导游对话系统的相关技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (149)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107644011A (en) * 2016-07-20 2018-01-30 百度（美国）有限责任公司 System and method for the extraction of fine granularity medical bodies
CN107644011B (en) * 2016-07-20 2023-11-07 百度（美国）有限责任公司 System and method for fine-grained medical entity extraction
CN106339366A (en) * 2016-08-08 2017-01-18 北京百度网讯科技有限公司 Method and device for requirement identification based on artificial intelligence (AI)
CN106339366B (en) * 2016-08-08 2019-05-31 北京百度网讯科技有限公司 The method and apparatus of demand identification based on artificial intelligence
CN106295187A (en) * 2016-08-11 2017-01-04 中国科学院计算技术研究所 Construction of knowledge base method and system towards intelligent clinical auxiliary decision-making support system
CN106503194A (en) * 2016-11-02 2017-03-15 大唐软件技术股份有限公司 Information getting method and device
CN106844335A (en) * 2016-12-21 2017-06-13 海航生态科技集团有限公司 Natural language processing method and device
CN106815745A (en) * 2016-12-30 2017-06-09 北京三快在线科技有限公司 Vegetable recommends method and system
CN106919655A (en) * 2017-01-24 2017-07-04 网易（杭州）网络有限公司 A kind of answer provides method and apparatus
CN108446286B (en) * 2017-02-16 2023-04-25 阿里巴巴集团控股有限公司 Method, device and server for generating natural language question answers
CN108446286A (en) * 2017-02-16 2018-08-24 阿里巴巴集团控股有限公司 A kind of generation method, device and the server of the answer of natural language question sentence
CN107169013A (en) * 2017-03-31 2017-09-15 北京三快在线科技有限公司 A kind of processing method and processing device of dish information
CN107169013B (en) * 2017-03-31 2018-01-19 北京三快在线科技有限公司 A kind of processing method and processing device of dish information
CN107239481A (en) * 2017-04-12 2017-10-10 北京大学 A kind of construction of knowledge base method towards multi-source network encyclopaedia
CN106897273B (en) * 2017-04-12 2018-02-06 福州大学 A kind of network security dynamic early-warning method of knowledge based collection of illustrative plates
CN106897273A (en) * 2017-04-12 2017-06-27 福州大学 A kind of network security dynamic early-warning method of knowledge based collection of illustrative plates
CN107239481B (en) * 2017-04-12 2021-03-12 北京大学 Knowledge base construction method for multi-source network encyclopedia
CN107247613A (en) * 2017-04-25 2017-10-13 北京航天飞行控制中心 Sentence analytic method and sentence resolver
CN107256226B (en) * 2017-04-28 2018-10-30 北京神州泰岳软件股份有限公司 A kind of construction method and device of knowledge base
CN107256226A (en) * 2017-04-28 2017-10-17 北京神州泰岳软件股份有限公司 The construction method and device of a kind of knowledge base
CN107193798B (en) * 2017-05-17 2019-06-04 南京大学 A kind of examination question understanding method in rule-based examination question class automatically request-answering system
CN107193798A (en) * 2017-05-17 2017-09-22 南京大学 A kind of examination question understanding method in rule-based examination question class automatically request-answering system
CN107239450A (en) * 2017-06-02 2017-10-10 上海对岸信息科技有限公司 Natural language method is handled based on Interaction context
CN107423437A (en) * 2017-08-04 2017-12-01 逸途（北京）科技有限公司 A kind of Question-Answering Model optimization method based on confrontation network intensified learning
CN107423439A (en) * 2017-08-04 2017-12-01 逸途（北京）科技有限公司 A kind of Chinese charater problem mapping method based on LDA
CN107423437B (en) * 2017-08-04 2020-09-01 逸途（北京）科技有限公司 Question-answer model optimization method based on confrontation network reinforcement learning
CN107748757B (en) * 2017-09-21 2021-05-07 北京航空航天大学 Question-answering method based on knowledge graph
CN107748757A (en) * 2017-09-21 2018-03-02 北京航空航天大学 A kind of answering method of knowledge based collection of illustrative plates
CN109684354A (en) * 2017-10-18 2019-04-26 北京国双科技有限公司 Data query method and apparatus
CN107818148A (en) * 2017-10-23 2018-03-20 南京南瑞集团公司 Self-service query and statistical analysis method based on natural language processing
CN107885844A (en) * 2017-11-10 2018-04-06 南京大学 Automatic question-answering method and system based on systematic searching
CN107895037B (en) * 2017-11-28 2022-05-03 北京百度网讯科技有限公司 Question and answer data processing method, device, equipment and computer readable medium
CN107895037A (en) * 2017-11-28 2018-04-10 北京百度网讯科技有限公司 A kind of question and answer data processing method, device, equipment and computer-readable medium
CN108052577A (en) * 2017-12-08 2018-05-18 北京百度网讯科技有限公司 A kind of generic text content mining method, apparatus, server and storage medium
WO2019114430A1 (en) * 2017-12-15 2019-06-20 王碧波 Natural language question understanding method and apparatus, and electronic device
CN110020015A (en) * 2017-12-29 2019-07-16 中国科学院声学研究所 A kind of conversational system answers generation method and system
CN108287822A (en) * 2018-01-23 2018-07-17 北京容联易通信息技术有限公司 A kind of Chinese Similar Problems generation System and method for
CN109344385A (en) * 2018-01-30 2019-02-15 深圳壹账通智能科技有限公司 Natural language processing method, apparatus, computer equipment and storage medium
CN109344385B (en) * 2018-01-30 2020-12-22 深圳壹账通智能科技有限公司 Natural language processing method, device, computer equipment and storage medium
WO2019148797A1 (en) * 2018-01-30 2019-08-08 深圳壹账通智能科技有限公司 Natural language processing method, device, computer apparatus, and storage medium
CN108376287A (en) * 2018-03-02 2018-08-07 复旦大学 Multi-valued attribute segmenting device based on CN-DBpedia and method
CN108491378A (en) * 2018-03-08 2018-09-04 国网福建省电力有限公司 Power information O＆M intelligent response system
CN110362662A (en) * 2018-04-09 2019-10-22 北京京东尚科信息技术有限公司 Data processing method, device and computer readable storage medium
CN108549694A (en) * 2018-04-16 2018-09-18 南京云问网络技术有限公司 The processing method of temporal information in a kind of text
CN108549694B (en) * 2018-04-16 2021-11-23 南京云问网络技术有限公司 Method for processing time information in text
CN108549710A (en) * 2018-04-20 2018-09-18 腾讯科技（深圳）有限公司 Intelligent answer method, apparatus, storage medium and equipment
CN108549710B (en) * 2018-04-20 2023-06-27 腾讯科技（深圳）有限公司 Intelligent question-answering method, device, storage medium and equipment
WO2019205705A1 (en) * 2018-04-28 2019-10-31 厦门快商通信息技术有限公司 Semantic-framework-based human-machine conversation method and system
CN108595696A (en) * 2018-05-09 2018-09-28 长沙学院 A kind of human-computer interaction intelligent answering method and system based on cloud platform
CN108733359A (en) * 2018-06-14 2018-11-02 北京航空航天大学 A kind of automatic generation method of software program
CN108984527A (en) * 2018-07-10 2018-12-11 广州极天信息技术股份有限公司 A kind of method for recognizing semantics and device based on concept
CN110852110A (en) * 2018-07-25 2020-02-28 富士通株式会社 Target sentence extraction method, question generation method, and information processing apparatus
CN110852110B (en) * 2018-07-25 2023-08-04 富士通株式会社 Target sentence extraction method, question generation method, and information processing apparatus
CN110851560B (en) * 2018-07-27 2023-03-10 杭州海康威视数字技术股份有限公司 Information retrieval method, device and equipment
CN110851560A (en) * 2018-07-27 2020-02-28 杭州海康威视数字技术股份有限公司 Information retrieval method, device and equipment
CN110858100B (en) * 2018-08-22 2023-10-20 北京搜狗科技发展有限公司 Method and device for generating association candidate words
CN110858100A (en) * 2018-08-22 2020-03-03 北京搜狗科技发展有限公司 Method and device for generating association candidate words
CN109344236B (en) * 2018-09-07 2020-09-04 暨南大学 Problem similarity calculation method based on multiple characteristics
CN109344236A (en) * 2018-09-07 2019-02-15 暨南大学 One kind being based on the problem of various features similarity calculating method
CN109408811A (en) * 2018-09-29 2019-03-01 联想(北京)有限公司 A kind of data processing method and server
CN109408811B (en) * 2018-09-29 2021-10-22 联想(北京)有限公司 Data processing method and server
CN110990541A (en) * 2018-09-30 2020-04-10 北京国双科技有限公司 Method and device for realizing question answering
CN109613917A (en) * 2018-11-02 2019-04-12 广州城市职业学院 A kind of question and answer robot and its implementation
CN109522418A (en) * 2018-11-08 2019-03-26 杭州费尔斯通科技有限公司 A kind of automanual knowledge mapping construction method
CN109522418B (en) * 2018-11-08 2020-05-12 杭州费尔斯通科技有限公司 Semi-automatic knowledge graph construction method
CN111241841A (en) * 2018-11-13 2020-06-05 第四范式（北京）技术有限公司 Semantic analysis method and device, computing equipment and readable medium
CN111241841B (en) * 2018-11-13 2024-04-05 第四范式（北京）技术有限公司 Semantic analysis method and device, computing device and readable medium
CN111210824A (en) * 2018-11-21 2020-05-29 深圳绿米联创科技有限公司 Voice information processing method and device, electronic equipment and storage medium
CN111210824B (en) * 2018-11-21 2023-04-07 深圳绿米联创科技有限公司 Voice information processing method and device, electronic equipment and storage medium
CN109753541A (en) * 2018-12-10 2019-05-14 北京明略软件系统有限公司 A kind of relational network construction method and device, computer readable storage medium
CN109684448A (en) * 2018-12-17 2019-04-26 北京北大软件工程股份有限公司 A kind of intelligent answer method
CN109684448B (en) * 2018-12-17 2021-01-12 北京北大软件工程股份有限公司 Intelligent question and answer method
CN109766994A (en) * 2018-12-25 2019-05-17 华东师范大学 A kind of neural network framework of natural language inference
CN111400458A (en) * 2018-12-27 2020-07-10 上海智臻智能网络科技股份有限公司 Automatic generalization method and device
CN109710939B (en) * 2018-12-28 2023-06-09 北京百度网讯科技有限公司 Method and device for determining theme
CN109710939A (en) * 2018-12-28 2019-05-03 北京百度网讯科技有限公司 Method and apparatus for determining theme
CN109902087B (en) * 2019-02-02 2023-05-30 上海来也伯特网络科技有限公司 Data processing method and device for questions and answers and server
CN109902087A (en) * 2019-02-02 2019-06-18 上海奔影网络科技有限公司 For the data processing method and device of question and answer, server
US11487795B2 (en) 2019-02-21 2022-11-01 Yangzhou University Template-based automatic software bug question and answer method
WO2020168702A1 (en) * 2019-02-21 2020-08-27 扬州大学 Template-based automatic software defect question and answer method
CN111886601A (en) * 2019-03-01 2020-11-03 卡德乐人工智能私人有限公司 System and method for adaptive question answering
CN111886601B (en) * 2019-03-01 2024-03-01 卡德乐人工智能私人有限公司 System and method for adaptive question-answering
CN109949637B (en) * 2019-03-13 2021-07-16 广东小天才科技有限公司 Automatic answering method and device for objective questions
CN109949637A (en) * 2019-03-13 2019-06-28 广东小天才科技有限公司 A kind of objective item purpose answers method and apparatus automatically
CN110147436A (en) * 2019-03-18 2019-08-20 清华大学 A kind of mixing automatic question-answering method based on padagogical knowledge map and text
CN110147436B (en) * 2019-03-18 2021-02-26 清华大学 Education knowledge map and text-based hybrid automatic question-answering method
CN109977370A (en) * 2019-03-19 2019-07-05 河海大学常州校区 It is a kind of based on the question and answer of document collection partition to method for auto constructing
CN109977370B (en) * 2019-03-19 2023-06-16 河海大学常州校区 Automatic question-answer pair construction method based on document structure tree
CN110019687A (en) * 2019-04-11 2019-07-16 宁波深擎信息科技有限公司 A kind of more intention assessment systems, method, equipment and the medium of knowledge based map
CN110019687B (en) * 2019-04-11 2021-03-23 宁波深擎信息科技有限公司 Multi-intention recognition system, method, equipment and medium based on knowledge graph
CN109977421A (en) * 2019-04-15 2019-07-05 南京邮电大学 A kind of Knowledge Base of Programming subjects answering system after class
CN110096580A (en) * 2019-04-24 2019-08-06 北京百度网讯科技有限公司 A kind of FAQ dialogue method, device and electronic equipment
CN110096580B (en) * 2019-04-24 2022-05-24 北京百度网讯科技有限公司 FAQ conversation method and device and electronic equipment
WO2020221142A1 (en) * 2019-04-28 2020-11-05 华为技术有限公司 Picture book-based question and answer interaction method and electronic device
CN111858866A (en) * 2019-04-30 2020-10-30 广东小天才科技有限公司 Semantic analysis method and device based on triples
CN110334179A (en) * 2019-05-22 2019-10-15 深圳追一科技有限公司 Question and answer processing method, device, computer equipment and storage medium
CN110347808A (en) * 2019-05-28 2019-10-18 成都美美臣科技有限公司 One e-commerce website intelligent robot customer service construction method
CN110532358A (en) * 2019-07-05 2019-12-03 东南大学 A kind of template automatic generation method towards knowledge base question and answer
CN110532358B (en) * 2019-07-05 2023-08-22 东南大学 Knowledge base question-answering oriented template automatic generation method
CN110321544A (en) * 2019-07-08 2019-10-11 北京百度网讯科技有限公司 Method and apparatus for generating information
CN110321544B (en) * 2019-07-08 2023-07-25 北京百度网讯科技有限公司 Method and device for generating information
CN110349477B (en) * 2019-07-16 2022-01-07 长沙酷得网络科技有限公司 Programming error repairing method, system and server based on historical learning behaviors
CN110349477A (en) * 2019-07-16 2019-10-18 湖南酷得网络科技有限公司 A kind of misprogrammed restorative procedure, system and server based on history learning behavior
CN110427471A (en) * 2019-07-26 2019-11-08 四川长虹电器股份有限公司 A kind of natural language question-answering method and system of knowledge based map
CN110532366A (en) * 2019-09-03 2019-12-03 出门问问(武汉)信息科技有限公司 A kind of pattern rule management method, language generation method, apparatus and storage equipment
CN110852067A (en) * 2019-10-10 2020-02-28 杭州量之智能科技有限公司 Question analysis method for non-entity word dependency extraction based on SVM
CN110727780A (en) * 2019-10-17 2020-01-24 福建天晴数码有限公司 System and method for automatically expanding acquaintance text
CN110727782A (en) * 2019-10-22 2020-01-24 苏州思必驰信息科技有限公司 Question and answer corpus generation method and system
CN111125150B (en) * 2019-12-26 2023-12-26 成都航天科工大数据研究院有限公司 Search method for industrial field question-answering system
CN111125150A (en) * 2019-12-26 2020-05-08 成都航天科工大数据研究院有限公司 Industrial field question-answering system retrieval method
CN111159345A (en) * 2019-12-27 2020-05-15 中国矿业大学 Chinese knowledge base answer obtaining method and device
CN111159345B (en) * 2019-12-27 2023-09-05 中国矿业大学 Chinese knowledge base answer acquisition method and device
CN111339269A (en) * 2020-02-20 2020-06-26 来康科技有限责任公司 Knowledge graph question-answer training and application service system with automatically generated template
CN111339269B (en) * 2020-02-20 2023-09-26 来康科技有限责任公司 Knowledge graph question-answering training and application service system capable of automatically generating templates
CN111382256A (en) * 2020-03-20 2020-07-07 北京百度网讯科技有限公司 Information recommendation method and device
CN111382256B (en) * 2020-03-20 2024-04-09 北京百度网讯科技有限公司 Information recommendation method and device
CN111553160B (en) * 2020-04-24 2024-02-02 北京北大软件工程股份有限公司 Method and system for obtaining question answers in legal field
CN111651569A (en) * 2020-04-24 2020-09-11 中国电力科学研究院有限公司 Knowledge base question-answering method and system in electric power field
CN111651569B (en) * 2020-04-24 2022-04-08 中国电力科学研究院有限公司 Knowledge base question-answering method and system in electric power field
CN111553160A (en) * 2020-04-24 2020-08-18 北京北大软件工程股份有限公司 Method and system for obtaining answers to question sentences in legal field
CN111625623A (en) * 2020-04-29 2020-09-04 奇安信科技集团股份有限公司 Text theme extraction method, text theme extraction device, computer equipment, medium and program product
CN111625623B (en) * 2020-04-29 2023-09-08 奇安信科技集团股份有限公司 Text theme extraction method, text theme extraction device, computer equipment, medium and program product
CN111708800A (en) * 2020-05-27 2020-09-25 北京百度网讯科技有限公司 Query method and device and electronic equipment
WO2021135103A1 (en) * 2020-05-29 2021-07-08 平安科技（深圳）有限公司 Method and apparatus for semantic analysis, computer device, and storage medium
CN111709250A (en) * 2020-06-11 2020-09-25 北京百度网讯科技有限公司 Method, apparatus, electronic device, and storage medium for information processing
CN111459973A (en) * 2020-06-16 2020-07-28 四川大学 Case type retrieval method and system based on case situation triple information
CN111459973B (en) * 2020-06-16 2020-10-23 四川大学 Case type retrieval method and system based on case situation triple information
CN111949781A (en) * 2020-08-06 2020-11-17 贝壳技术有限公司 Intelligent interaction method and device based on natural sentence syntactic analysis
CN112256847A (en) * 2020-09-30 2021-01-22 昆明理工大学 Knowledge base question-answering method integrating fact texts
CN112287080A (en) * 2020-10-23 2021-01-29 平安科技（深圳）有限公司 Question sentence rewriting method and device, computer equipment and storage medium
CN112287080B (en) * 2020-10-23 2023-10-03 平安科技（深圳）有限公司 Method and device for rewriting problem statement, computer device and storage medium
CN112347121A (en) * 2020-11-02 2021-02-09 中科曙光南京研究院有限公司 Configurable method and system for converting natural language into sql
CN112347121B (en) * 2020-11-02 2024-05-28 中科曙光南京研究院有限公司 Configurable natural language sql conversion method and system
CN112380848B (en) * 2020-11-19 2022-04-26 平安科技（深圳）有限公司 Text generation method, device, equipment and storage medium
CN112380848A (en) * 2020-11-19 2021-02-19 平安科技（深圳）有限公司 Text generation method, device, equipment and storage medium
CN112417170B (en) * 2020-11-23 2023-11-14 南京大学 Relationship linking method for incomplete knowledge graph
CN112417170A (en) * 2020-11-23 2021-02-26 南京大学 Relation linking method for incomplete knowledge graph
CN112182230A (en) * 2020-11-27 2021-01-05 北京健康有益科技有限公司 Text data classification method and device based on deep learning
CN112733547A (en) * 2020-12-28 2021-04-30 北京计算机技术及应用研究所 Chinese question semantic understanding method by utilizing semantic dependency analysis
CN112906559A (en) * 2021-02-10 2021-06-04 网易有道信息技术（北京）有限公司 Machine-implemented method for correcting formulas and related product
CN113590782B (en) * 2021-07-28 2024-02-09 北京百度网讯科技有限公司 Training method of reasoning model, reasoning method and device
CN113590782A (en) * 2021-07-28 2021-11-02 北京百度网讯科技有限公司 Training method, reasoning method and device of reasoning model
CN113761940A (en) * 2021-09-09 2021-12-07 杭州隆埠科技有限公司 News subject judgment method, equipment and computer readable medium
CN113761940B (en) * 2021-09-09 2023-08-11 杭州隆埠科技有限公司 News main body judging method, equipment and computer readable medium
CN114357123A (en) * 2022-03-18 2022-04-15 北京创新乐知网络技术有限公司 Data matching method, device and equipment based on hierarchical structure and storage medium
CN115080742B (en) * 2022-06-24 2023-09-05 北京百度网讯科技有限公司 Text information extraction method, apparatus, device, storage medium, and program product
CN115080742A (en) * 2022-06-24 2022-09-20 北京百度网讯科技有限公司 Text information extraction method, device, equipment, storage medium and program product
CN117332097B (en) * 2023-11-30 2024-03-01 北京大数据先进技术研究院 Knowledge question-answering method, device and product based on space-time semantic constraint
CN117332097A (en) * 2023-11-30 2024-01-02 北京大数据先进技术研究院 Knowledge question-answering method, device and product based on space-time semantic constraint

Also Published As

Publication number Publication date
CN105701253B (en) 2019-03-26

Similar Documents

Publication Publication Date Title
CN105701253B (en) The knowledge base automatic question-answering method of Chinese natural language question semanteme
JP7064262B2 (en) Knowledge graph understanding support system based on natural language generation technology
Khan et al. A novel natural language processing (NLP)–based machine translation model for English to Pakistan sign language translation
Szekely et al. Connecting the smithsonian american art museum to the linked data cloud
US10853357B2 (en) Extensible automatic query language generator for semantic data
CN106776711A (en) A kind of Chinese medical knowledge mapping construction method based on deep learning
WO2015161338A1 (en) Ontology aligner method, semantic matching method and apparatus
CN104252533A (en) Search method and search device
Jin et al. ComQA: Question answering over knowledge base via semantic matching
CN108665141B (en) Method for automatically extracting emergency response process model from emergency plan
CN111553160B (en) Method and system for obtaining question answers in legal field
CN109840255A (en) Reply document creation method, device, equipment and storage medium
CN105760462A (en) Man-machine interaction method and device based on associated data query
CN112417161B (en) Method and storage device for recognizing upper and lower relationships of knowledge graph based on mode expansion and BERT classification
Hu et al. Natural language aggregate query over RDF data
Lopez et al. QuerioDALI: question answering over dynamic and linked knowledge graphs
CN110119404B (en) Intelligent access system and method based on natural language understanding
CN108491399A (en) Chinese to English machine translation method based on context iterative analysis
Prudhomme et al. Automatic Integration of Spatial Data into the Semantic Web.
Li et al. Neural factoid geospatial question answering
Rowe et al. Data. dcs: Converting Legacy Data into Linked Data.
Zhang et al. FactQA: Question answering over domain knowledge graph based on two-level query expansion
CN117473054A (en) Knowledge graph-based general intelligent question-answering method and device
To et al. Question-answering system with linguistic terms over RDF knowledge graphs
Nguyen et al. A vietnamese question answering system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant