Research on Chinese Sentence Similarity Calculation Method Based on Multiple Features

2018 ◽  
Author(s):  
Chenyang Wu ◽  
Jinbo Wang ◽  
Xiaohua Wang ◽  
Yunyun Ma
Keyword(s):  
Calculation Method ◽  
Multiple Features ◽  
Sentence Similarity ◽  
Similarity Calculation

Research on the Subjective Topic Grading Agorithm Based on the Computer Course

2014 ◽  
Vol 1049-1050 ◽  
pp. 1514-1517
Author(s):  
Sai Dong Lv ◽  
Ji Li Xie
Keyword(s):  
Semantic Similarity ◽  
Calculation Method ◽  
Original Method ◽  
Sentence Similarity ◽  
Similarity Calculation ◽  
Similarity Algorithm ◽  
Computer Course ◽  
Calculation Results ◽  
Multi Level ◽  
Level Fusion

Subjective question marking system at present is affected by the attention of people, the subjective topic grading principles are common contrast degree of exam questions similar to those of the reference answer, and based on the improved semantic similarity algorithm, calculation of sentence similarity, the similarity degree of exam questions and reference answer is obtained, thus give scores.And design based on semantic similarity experiment, the experiment results show that the proposed multi-level fusion similarity calculation method to improve the original method, on the basis of integration advantages of various methods, make the calculation results meet the requirements of the scoring system.

Similarity detection of English text and teaching evaluation based on improved TCUSS clustering algorithm

2020 ◽  
pp. 1-11
Author(s):  
Yu Wang
Keyword(s):  
Language Processing ◽  
Calculation Method ◽  
Clustering Algorithm ◽  
Research Result ◽  
Structural Features ◽  
English Text ◽  
Support Vector ◽  
Similarity Calculation ◽  
Other Information ◽  
Calculation Task

The semantic similarity calculation task of English text has important influence on other fields of natural language processing and has high research value and application prospect. At present, research on the similarity calculation of short texts has achieved good results, but the research result on long text sets is still poor. This paper proposes a similarity calculation method that combines planar features with structured features and uses support vector regression models. Moreover, this paper uses PST and PDT to represent the syntax, semantics and other information of the text. In addition, through the two structural features suitable for text similarity calculation, this paper proposes a similarity calculation method combining structural features with Tree-LSTM model. Experiments show that this method provides a new idea for interest network extraction.

An Analysis Method of Semantic Relevancy on Controlled Tag

2012 ◽  
Vol 263-266 ◽  
pp. 1588-1592
Author(s):  
Jiu Qing Li ◽  
Chi Zhang ◽  
Peng Zhou Zhang
Keyword(s):  
Semantic Similarity ◽  
Calculation Method ◽  
Domain Ontology ◽  
Analysis Method ◽  
Semantic Correlation ◽  
Retrieval Efficiency ◽  
Similarity Calculation

To solve resource-tagging inefficiency and low-precision retrieval in special field, an analysis method of tag semantic relevancy based on controlled database was proposed. The characteristic of special field and building method for controlled database were discussed. Domain ontology correlation calculation method was used to get semantic correlation. The tag semantic similarity calculation method was developed for semantic similarity, and normalization was used to increase the similarity accuracy. With semantic correlation and similarity as parameters, the semantic relevancy in special field can be obtained. This method was used successfully in the special field of actual projects, improved resource-tagging and retrieval efficiency.

The Calculation Method of Similarity Degree for City Logistics Facilities

2011 ◽  
Vol 219-220 ◽  
pp. 1621-1624
Author(s):  
Guo Qi Li ◽  
Si Jing Liu
Keyword(s):  
Computer Science ◽  
Calculation Method ◽  
Processing Method ◽  
City Logistics ◽  
Calculation Formula ◽  
Calculation Methods ◽  
Similarity Degree ◽  
Qualitative And Quantitative ◽  
Similarity Calculation ◽  
Similarity Dimension

For the multi-attribute characteristics of scale, quantity, service radius and target of service in city logistics facilities，this paper considered the similar phenomena between city logistics facilities caused by the interaction of different social and economic attributes. Based on the analysis of the similarity degree calculation methods in computer science and mechanical engineering, it proposed two calculation methods of similarity degree in city logistics facilities. The qualitative and quantitative attributes were considered separately in the first method, the quantitative attributes were disposed by triangular fuzzy number.The similarity dimension was introduced as the basis of the similarity degree calculation in the second method. A merge processing method was used to incorporate all similar characteristics of every similarity dimension and a similarity calculation formula was deduced from the theory of similarity.

Short Tamil sentence similarity calculation using knowledge-based and corpus-based similarity measures

2017 ◽  
Author(s):  
Anutharsha Selvarasa ◽  
Nilasini Thirunavukkarasu ◽  
Niveathika Rajendran ◽  
Chinthoorie Yogalingam ◽  
Surangika Ranathunga ◽  
...  
Keyword(s):  
Similarity Measures ◽  
Knowledge Based ◽  
Sentence Similarity ◽  
Similarity Calculation

Study on Application of Domain Ontology in Semantic Information Retrieval

2013 ◽  
Vol 433-435 ◽  
pp. 1662-1665
Author(s):  
Huan Hai Yang ◽  
Ming Yu Sun
Keyword(s):  
Information Retrieval ◽  
Semantic Similarity ◽  
Calculation Method ◽  
Semantic Information ◽  
Domain Ontology ◽  
Semantic Retrieval ◽  
Retrieval Model ◽  
Retrieval Method ◽  
Similarity Calculation ◽  
Semantic Information Retrieval

Considering weakness of the traditional retrieval method based on keyword matching, the paper introduced semantic into information retrieval, and proposed a semantic retrieval model based on ontology. The paper offered a construction method of domain ontology and implemented semantic reasoning using Jena and improved a semantic similarity calculation method.

Sign in / Sign up

Export Citation Format

Share Document