CN105843897B - A kind of intelligent Answer System towards vertical field - Google Patents
A kind of intelligent Answer System towards vertical field Download PDFInfo
- Publication number
- CN105843897B CN105843897B CN201610167602.5A CN201610167602A CN105843897B CN 105843897 B CN105843897 B CN 105843897B CN 201610167602 A CN201610167602 A CN 201610167602A CN 105843897 B CN105843897 B CN 105843897B
- Authority
- CN
- China
- Prior art keywords
- module
- sentence
- word
- vocabulary
- similarity
- 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
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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
A kind of intelligent Answer System towards vertical field, including put question to module (1), preprocessing module (2), participle and lexical normalisation module (3), purification word module (4), synonym expansion module (5), vocabulary extension or removing module (6), sentence similarity computing module (7) and reply output module (8).The present invention calculates the similarity of user's question sentence by building domain body, calculates dependent on participle technique, the building of domain body, body similarity.The invention has the advantages that application field ontology more accurately understands that user puts question to and is intended to by the sentence similarity algorithm, sentence similarity is calculated, the accuracy rate of question answering system is improved.
Description
Technical field
The present invention relates to a kind of intelligent Answer Systems towards vertical field, have to the semantic analysis accuracy rate in vertical field
Significant and effect.
Background technique
It is divided according to the realization technology of question answering system, comprising: be based on the question answering system of frequently asked questions (FAQ), based on letter
It ceases the question answering system retrieved, the question answering system based on Question Classification and is based on resource description framework (Resource
Description Framework) RDF query question answering system.
Question answering system based on frequently asked questions constructs FAQs (FAQ) question and answer pair, depends on user's question sentence in realization
With the similarity calculation of question sentence in FAQ.In the development process of FAQ question answering system, need to identify the intention of user's question sentence, to two
A sentence carries out similarity calculation, to return to query result.The relevant technologies process of existing FAQ question answering system are as follows: to sentence
After being segmented, removing the pretreatment works such as stop words, word standardization, inverted index table is established, with VSM TF-IDF algorithm
Calculate the similarity of the word array of two sentences.
Question answering system based on information retrieval, the information source of this system are usually the document on network, are returned
Answer is directly extracted from document.
Based on the question answering system of customer problem classification, corresponding template usually is constructed to every a kind of problem and is handled, is increased
By force to the understanding of problem, the accuracy rate of system is improved.
Based on RDF(Resource Description Framework resource description framework, one kind is for describing Web money
The markup language in source) core of question answering system of inquiry is natural language question sentence to be converted into the standard query language of RDF, usually
It is W3C given query language SPARQL, class, example or the attribute word in natural language question sentence being mapped as in ontology.
However the prior art has using the similarity calculating method for being based on " Hownet ", still when calculating Words similarity
Enough semantic analyses are lacked for the vertical field of profession.And the prior art does not consider field when calculating sentence similarity
The weight of vocabulary lacks enough semantic analyses for the vocabulary in the vertical field of profession.
Technical term explanation of the present invention:
Domain body: domain body gives the basic terms and relationship for constituting related fields vocabulary, and combines this
A little terms and relationship define the rules of these vocabulary extensions.
Participle technique: participle is exactly the words recognition of sentence and carry out part-of-speech tagging.
Hownet: " Hownet " (HowNet) is the detailed semantic knowledge dictionary of a comparison.With Chinese and english word institute's generation
The concept of table is description object, is substantially interior to disclose the relationship between concept and concept and between attribute possessed by concept
The commonsense knowledge base of appearance.
Inverted index table: a table is established to word, and records the position of problem corresponding to word.Due to not being by recording
It determines attribute value, but determines the position of record by attribute value, thus referred to as inverted index (inverted index).
VSM: the processing to content of text is reduced to vector space by vector space model (Vector Space Model)
In vector operation, semantic similarity of the similarity of two vector operations as two sentences.
TF-IDF: term frequency-inverse document frequency method (term frequency-inverse document frequency),
On the basis of VSM algorithm, the weight of word is determined according to the frequency of word, calculates the similarity of two sentences.
Summary of the invention
Realization is organically combined the present invention is based on FAQ and based on RDF query technology, proposes a kind of new question answering system and processing
Process improves the accuracy rate of intelligent automatically request-answering system to enhance intelligent Answer System semantic analysis ability.
The technical scheme is that the present invention calculates the similarity of user's question sentence by building domain body, depend on
Participle technique, the building of domain body, body similarity calculate.
The invention has the advantages that by the sentence similarity algorithm, application field ontology more accurately understands use
Family, which is putd question to, to be intended to, and is calculated sentence similarity, is improved the accuracy rate of question answering system.
Detailed description of the invention
Fig. 1 is that present system constitutes block diagram;
Fig. 2 is groundwork program flow diagram of the present invention;
Fig. 3 is the schematic diagram of the taxonomic structure embodiment of ontology of the present invention;
Fig. 4 is the structural schematic diagram of a specific Noumenon property of the invention;
Fig. 5 is the flow chart of working procedure one embodiment of the present invention;
Fig. 6 is ontology baby's character classification by age structural schematic diagram of the invention.
Specific embodiment
Referring to Fig. 1, a kind of intelligent Answer System towards vertical field of the present invention is based primarily upon computer system, including
Consisting of part:
(1) module 1 is putd question to: for inputting (proposition) problem to system.It can be inputted using keyboard, voice input is hand-written
(plate) input, is inputted using image collecting device.
(2) preprocessing module 2: including vertical domain body (database), for by the class in ontology, attribute, Instance Name
Title is added in dictionary for word segmentation, and marks corresponding part of speech.
(3) participle and lexical normalisation module 3: for segmenting to question sentence, and carrying out word standardization, and mark is each
Classification marker in the part of speech and ontology of word.
(4) purify word module 4: for carrying out stop words to the set after participle, remove no practical significance modal particle,
Greeting word.
(5) synonym expansion module 5: for arranging the related Chinese thesaurus in vertical field, the meaning of a word is extended.
(6) ontology expansion module 6: for judging the lexical set after participle, if the vocabulary in ontology, to word
Relationship between remittance is analyzed, and is extended or is deleted, and weight of the vocabulary in sentence is arranged;If not the word in ontology
It converges, is calculated according to the similarity of common words.
(7) it sentence similarity computing module: in conjunction with weight of the vocabulary in sentence, calculates candidate in the library FAQ and asks
The sentence similarity of topic and question sentence.
(8) output module is replied: for exporting the answer of problem.
Referring to fig. 2, groundwork process of the invention includes:
(1) it pre-processes: constructing vertical domain body, the class in ontology, attribute, instance name are added to dictionary for word segmentation
In, and mark corresponding part of speech.
(2) word standardization is segmented and carried out to question sentence, marks the contingency table in the part of speech and ontology of each word
Note.
(3) stop words is carried out to the set after participle, removes modal particle, the greeting word of no practical significance.
(4) the related Chinese thesaurus for arranging vertical field, is extended the meaning of a word.
(5) lexical set after participle is judged, if the vocabulary in ontology, the relationship vocabulary is divided
Analysis, is extended or deletes, and weight of the vocabulary in sentence is arranged;If not the vocabulary in ontology, according to common words
Similarity calculated.
(6) weight of the vocabulary in sentence is combined, the sentence similarity of candidate problem and question sentence in the library FAQ is calculated.
(7) the problem of exporting problem answers: sorting from high to low according to similarity, finally choosing similarity highest, which is used as, to be answered
Case.
System and workflow of the invention are described further below with reference to Fig. 3-Fig. 6.
1. being constructed about vertical domain ontology repository:
Classify to the knowledge in vertical field, analyzes the relationship between concept and its attribute, realize the table of domain knowledge
It reaches.
Class, example in domain body, attribute: class and object are similar in class and example and object-oriented, and attribute is retouched
State the relationship between class or example.
In Fig. 4, " place " is used as a class, has " Suzhou " as its example, there is the reality of a Hui Shi golden clothes series
Example " Wyeth Hui Shi _ 2 sections of Promil Gold milk powder 400g ", its place of production is Suzhou." place of production " connects two realities as attribute
Example.
2. the calculating of Words similarity in ontology:
Vocabulary corresponds to class, example or the attribute in ontology.All concepts form digraph, define parent and direct subclass
Distance be 1, class at a distance from the example be 1, attribute is respectively 1 at a distance from its domain and codomain, vocabulary W1, W2 away from
It is cumulative from according to above-mentioned definition.W0 is the nearest public father node of W1 and W2.Then the semantic similarity of two vocabulary uses formula:
+
Such as Fig. 3: with " Thing " for root node, depth 0, " Wyeth Hui Shi's _ 2 sections of Promil Gold milk powder 400g "
Depth is 5, and the depth of " Wyeth Hui Shi _ 3 sections of 400g of golden clothes Progress milk powder " is 5, their nearest public father node " gold
The depth of dress series " is 4, then their similarity is+ =0.80。
Or:
α is an adjustable parameter, indicates the value apart from its public father node when two Lexical Similarities are 0.5.
Such as Fig. 3: α=1.6 are set, with " Thing " for root node, depth 0, " Wyeth Hui Shi _ 2 sections of Promil Gold milk powder
400g " and " Wyeth Hui Shi _ 3 sections of 400g of golden clothes Progress milk powder ", they away from public father node " golden clothes series " recently away from
From being all 1, then their similarity are as follows:
+ =0.62。
Finally, sorting from high to low according to similarity, finally choose corresponding to first (similarity is highest) problem
Answer is exported as the final result asked a question, and by answer output module.
3. the determination of term weighing in question sentence:
Weight shared by different words is different in user's question sentence, for example question sentence " may I ask colored king's paper diaper either with or without day
This is original-pack? ", the term weighing of " flower king's paper diaper " and " Japan is original-pack " higher than " may I ask ", " having ", " not having ", " ".Specifically
Determination method be:
1) it safeguards and deactivates vocabulary, will " " " " " " etc. exclude without semantic word, it is not counted in sentence similarity calculating.
2) occur the subclass situation adjacent with its parent in question sentence and delete parent.Chinese will appear semantic the case where repeating,
Such as " Hui Shi milk powder " in Fig. 3, Hui Shi is the subclass of milk powder, the information of the information covering parent of subclass, and the information that subclass carries
Specific in further detail, in this case, we need to only consider information entrained by subclass.
3) dependence between word is analyzed, if W1, W2 are modified relationship, and is in the body the relationship of Subject-Verb
Then its object is added in vocabulary.
Such as Fig. 4: the Subject, Predicate and Object triple in shown ontology, " Wyeth Hui Shi _ 2 sections of Promil Gold milk powder 400g-production
Ground-Suzhou ", " Wyeth Hui Shi _ 2 sections of Promil Gold milk powder 400g " is subject, and " place of production " is predicate, and " Suzhou " serves as object
Role.
Example 1: question sentence: " where the place of production Wyeth Hui Shi _ 2 sections of 400g of Promil Gold milk powder is? ", Chinese " A's
" Suzhou " is added in vocabulary by B " in the case where A modifies B.
4) concept in domain body be with the higher vocabulary of the system degree of correlation, and with the increase of concept depth, concept
The information of carrying is more detailed, therefore the term weight in domain knowledge is higher than normal words, and the weight of vocabulary is with the depth of vocabulary
It spends and increases.
Weightw0= 1 +α
Wherein α is an adjustable parameter, adjusts the weight of concept, and the value that α is arranged herein is 1, indicates domain body
The weight of middle concept is between 1 and 2.
In Fig. 3, with " Thing " for root node, depth 0, the depth of " Hui Shi " is 3, it may be assumed that=3,=5, word
The weight of " Hui Shi " is WeightHui Shi = 1 + = 1.6。
5) it is calculated according to the number of words length of vocabulary:
Example 2: for the relationship of milk powder and baby's age, effect of the ontology information of building to semantic analysis.
As Fig. 6 constructs corresponding domain body, system can identify " four according to the number of segment of milk powder and the age of suitable baby
Month " it is in " 0-6 months " range, so that the problem of finding in model answer containing " 0-6 months ", aobvious on output module replying
Show that content is as follows:
Such as Fig. 5, user inputs question sentence " why rice flour has rancid taste? ", system participle while to word into
Row standardization, is standardized as " peculiar smell " for " rancid taste ";Stop words is removed, " there will be " " " to remove;Database is looked into fall to arrange rope
Draw the question sentence for containing [reason, rice flour, peculiar smell] in table, and problem is sorted according to the quantity containing keyword, takes first 15 to ask
Sentence is as candidate problem;Using VSM algorithm, successively calculate this 15 candidate problems participle go stop words result with [reason,
Rice flour, peculiar smell] similarity, sequence;The answer that similarity chooses the problem of highest returns.
Claims (2)
1. a kind of intelligent Answer System towards vertical field, which is characterized in that including consisting of part:
(1) module is putd question to: for inputting problem to system;
(2) preprocessing module: including vertical domain body, for the class in ontology, attribute, instance name to be added to participle word
In allusion quotation, and mark corresponding part of speech;
(3) participle and lexical normalisation module: for segmenting to question sentence, point in the part of speech and ontology of each word is marked
Class label;
(4) it purifies word module: for carrying out stop words to the set after participle, removing modal particle, the greeting of no practical significance
Word;
(5) synonym expansion module: for arranging the related Chinese thesaurus in vertical field, the meaning of a word is extended;
(6) ontology expansion module: for judging the lexical set after participle, if the vocabulary in ontology, between vocabulary
Relationship analyzed, be extended or delete, and weight of the vocabulary in sentence is set;If not the vocabulary in ontology,
It is calculated according to the similarity of common words;
(7) sentence similarity computing module: in conjunction with weight of the vocabulary in sentence, calculate in the library FAQ candidate problem with
The sentence similarity of question sentence;
(8) output module is replied: for exporting the answer of problem;
The workflow of the intelligent Answer System towards vertical field includes:
(1) it pre-processes: constructing vertical domain body, the class in ontology, attribute, instance name are added in dictionary for word segmentation, and
Mark corresponding part of speech;
(2) word standardization is segmented and carried out to question sentence, marks the classification marker in the part of speech and ontology of each word;
(3) stop words is carried out to the set after participle, removes modal particle, the greeting word of no practical significance;
(4) the related Chinese thesaurus for arranging vertical field, is extended the meaning of a word;
(5) lexical set after participle is judged, if the vocabulary in ontology, the relationship vocabulary is analyzed, into
Row extension is deleted, and weight of the vocabulary in sentence is arranged;If not the vocabulary in ontology, according to the similar of common words
Degree is calculated;
(6) weight of the vocabulary in sentence is combined, the sentence similarity of candidate problem and question sentence in the library FAQ is calculated;
(7) the problem of exporting problem answers: sorting from high to low according to similarity, finally choosing similarity highest is corresponding to be answered
Answer of the case as problem.
2. the intelligent Answer System according to claim 1 towards vertical field, which is characterized in that the enquirement module
Using keyboard, voice, the input of hand-written or image collecting device;The answer output module is using display, loudspeaker or beats
Print machine.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610167602.5A CN105843897B (en) | 2016-03-23 | 2016-03-23 | A kind of intelligent Answer System towards vertical field |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610167602.5A CN105843897B (en) | 2016-03-23 | 2016-03-23 | A kind of intelligent Answer System towards vertical field |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105843897A CN105843897A (en) | 2016-08-10 |
CN105843897B true CN105843897B (en) | 2019-03-26 |
Family
ID=56584443
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610167602.5A Active CN105843897B (en) | 2016-03-23 | 2016-03-23 | A kind of intelligent Answer System towards vertical field |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105843897B (en) |
Families Citing this family (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503101A (en) * | 2016-10-14 | 2017-03-15 | 五邑大学 | Electric business customer service automatically request-answering system sentence keyword extracting method |
CN106874441B (en) * | 2017-02-07 | 2024-03-05 | 腾讯科技(上海)有限公司 | Intelligent question-answering method and device |
CN108628882A (en) * | 2017-03-20 | 2018-10-09 | 北京京东尚科信息技术有限公司 | Method and system for prejudging problem |
CN107688608A (en) * | 2017-07-28 | 2018-02-13 | 合肥美的智能科技有限公司 | Intelligent sound answering method, device, computer equipment and readable storage medium storing program for executing |
CN107704559B (en) * | 2017-09-29 | 2020-06-05 | 北京软通智城科技有限公司 | Semantic understanding method and device |
CN107688667A (en) * | 2017-09-30 | 2018-02-13 | 平安科技(深圳)有限公司 | Intelligent robot client service method, electronic installation and computer-readable recording medium |
CN107657575A (en) * | 2017-09-30 | 2018-02-02 | 四川智美高科科技有限公司 | A kind of government affairs Intelligent Service terminal device and application method based on artificial intelligence |
CN107679039B (en) * | 2017-10-17 | 2020-12-29 | 北京百度网讯科技有限公司 | Method and device for determining statement intention |
CN107679231A (en) * | 2017-10-24 | 2018-02-09 | 济南浪潮高新科技投资发展有限公司 | A kind of vertical field and the implementation method of Opening field mixed type intelligent Answer System |
CN107992513B (en) * | 2017-10-25 | 2021-07-13 | 中兴通讯股份有限公司 | Information processing system and method for realizing information processing |
CN108121800B (en) * | 2017-12-21 | 2021-12-21 | 北京百度网讯科技有限公司 | Information generation method and device based on artificial intelligence |
CN108256009B (en) * | 2018-01-03 | 2022-02-15 | 国网江苏省电力有限公司电力科学研究院 | Method for improving answer accuracy of electric intelligent answer robot |
CN108509416B (en) * | 2018-03-20 | 2022-10-11 | 京东方科技集团股份有限公司 | Sentence meaning identification method and device, equipment and storage medium |
CN109710732B (en) * | 2018-11-19 | 2021-03-05 | 东软集团股份有限公司 | Information query method, device, storage medium and electronic equipment |
CN110532566B (en) * | 2019-09-03 | 2023-05-02 | 浪潮通用软件有限公司 | Method for realizing similarity calculation of questions in vertical field |
CN110866089B (en) * | 2019-11-14 | 2023-04-28 | 国家电网有限公司 | Robot knowledge base construction system and method based on synonymous multi-context analysis |
CN111324721A (en) * | 2020-03-16 | 2020-06-23 | 云南电网有限责任公司信息中心 | Method for constructing intelligent question-answering knowledge base |
CN112256864B (en) * | 2020-09-23 | 2024-05-14 | 北京捷通华声科技股份有限公司 | Multi-intention recognition method, device, electronic equipment and readable storage medium |
CN112307738B (en) * | 2020-11-11 | 2024-06-14 | 北京沃东天骏信息技术有限公司 | Method and device for processing text |
CN112668324B (en) * | 2020-12-04 | 2023-12-08 | 北京达佳互联信息技术有限公司 | Corpus data processing method and device, electronic equipment and storage medium |
CN112613611A (en) * | 2020-12-29 | 2021-04-06 | 上海永骁智能技术有限公司 | Tax knowledge base system based on knowledge graph |
CN113360596A (en) * | 2021-06-08 | 2021-09-07 | 南京大学 | Crowd-sourcing assistant implementation method based on tf-idf and inverted index |
CN113343708A (en) * | 2021-06-11 | 2021-09-03 | 北京声智科技有限公司 | Method and device for realizing statement generalization based on semantics |
CN116975206B (en) * | 2023-09-25 | 2023-12-08 | 华云天下(南京)科技有限公司 | Vertical field training method and device based on AIGC large model and electronic equipment |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101373532A (en) * | 2008-07-10 | 2009-02-25 | 昆明理工大学 | FAQ Chinese request-answering system implementing method in tourism field |
-
2016
- 2016-03-23 CN CN201610167602.5A patent/CN105843897B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101373532A (en) * | 2008-07-10 | 2009-02-25 | 昆明理工大学 | FAQ Chinese request-answering system implementing method in tourism field |
Non-Patent Citations (2)
Title |
---|
基于本体的语义相似度计算在营养知识问答系统中的应用;袁青波;《中国优秀硕士学位论文全文数据库信息科技辑》;20141115(第11期);第I138-550页 |
自动问答系统中的句子相似度算法的研究;周永梅等;《计算机技术与发展》;20120531;第22卷(第5期);第75-78页 |
Also Published As
Publication number | Publication date |
---|---|
CN105843897A (en) | 2016-08-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105843897B (en) | A kind of intelligent Answer System towards vertical field | |
JP5936698B2 (en) | Word semantic relation extraction device | |
CN103678564B (en) | Internet product research system based on data mining | |
CN109344236A (en) | One kind being based on the problem of various features similarity calculating method | |
CN106156272A (en) | A kind of information retrieval method based on multi-source semantic analysis | |
CN106055675B (en) | A kind of Relation extraction method based on convolutional neural networks and apart from supervision | |
US9195647B1 (en) | System, methods, and data structure for machine-learning of contextualized symbolic associations | |
CN106776562A (en) | A kind of keyword extracting method and extraction system | |
CN104933027A (en) | Open Chinese entity relation extraction method using dependency analysis | |
CN107562919B (en) | Multi-index integrated software component retrieval method and system based on information retrieval | |
Gómez-Adorno et al. | Automatic authorship detection using textual patterns extracted from integrated syntactic graphs | |
CN109960756A (en) | Media event information inductive method | |
CN110362678A (en) | A kind of method and apparatus automatically extracting Chinese text keyword | |
CN109214008A (en) | A kind of sentiment analysis method and system based on keyword extraction | |
CN105843796A (en) | Microblog emotional tendency analysis method and device | |
CN109255012A (en) | A kind of machine reads the implementation method and device of understanding | |
CN110399603A (en) | A kind of text-processing technical method and system based on sense-group division | |
CN106055633A (en) | Chinese microblog subjective and objective sentence classification method | |
US9262395B1 (en) | System, methods, and data structure for quantitative assessment of symbolic associations | |
CN107357918A (en) | Document representation method based on figure | |
JP5916016B2 (en) | Synonym determination device, synonym learning device, and program | |
Ali et al. | Word embedding based new corpus for low-resourced language: Sindhi | |
CN113392183A (en) | Characterization and calculation method of children domain map knowledge | |
Nieto Piña | Splitting rocks: Learning word sense representations from corpora and lexica | |
Dai | Construction of English and American literature corpus based on machine learning algorithm |
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 | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: Floor 5, Haier cloud Valley innovation block a, No. 1, Haier Road, Laoshan District, Qingdao, Shandong Province Patentee after: QINGDAO PENGHAI SOFTWARE Co.,Ltd. Address before: Laoshan District Green Road 266071 Shandong city of Qingdao province No. 19 22 11 floor Patentee before: HAIERSOFT Corp. |