An improved semantic similarity algorithm based on HowNet and CiLin-Reference-Cited by-同舟云学术

An improved semantic similarity algorithm based on HowNet and CiLin

Published:2020 Issue: Volume:309 Page:03004
ISSN:2261-236X
Container-title:MATEC Web of Conferences
language:
Short-container-title:MATEC Web Conf.

Author:

Wang Ying,Feng Xiwei,Zhang Yue,Chen Haiming,Xing Lijie

Abstract

This paper explores an improved method for the semantic similarity calculation of words combined with HowNet and CiLin. Firstly, we designing the algorithm based on HowNet’s sememe similarity improvement calculation, comprehensively considering the influence of each part of sememe on the overall meaning, and improving the calculation of word similarity based on HowNet by changing the specific calculation method of each part of sememe. At the same time, we adopt different strategies for the different results obtained in the similarity calculation of CiLin. The experimental RG data set proves that the modified Pearson coefficient of the method reaches 0.87.

Publisher

EDP Sciences

Subject

General Medicine

Link

https://www.matec-conferences.org/10.1051/matecconf/202030903004/pdf

Reference9 articles.

1. Qun Liu, Sujian Li. Vocabulary semantic similarity calculation based on HowNet. In The 3rd Chinese Vocabulary Semantics Seminar. 2002. pp:59–76

2. Seco N, Veale T, Hayes J. An intrinsic information content metric for semantic similarity in WordNet. In Proc of Eureopean Conference on Artificial Intelligence. 2004.pp:1089–1090.

Cited by 6 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. An Improved Algorithm of Word Semantic Similarity Based on HowNet;2022 16th IEEE International Conference on Signal Processing (ICSP);2022-10-21

2. A Novel Discrimination Structure for Assessing Text Semantic Similarity;網際網路技術學刊;2022-07

3. An Improved Term Frequency-Inverse Document Frequency Method Solving Multi-Text Label Problem;2022 Global Conference on Robotics, Artificial Intelligence and Information Technology (GCRAIT);2022-07

4. Application of LDA and word2vec to detect English off-topic composition;PLOS ONE;2022-02-25

5. Research on Component Retrieval and Matching Methods;2022 International Seminar on Computer Science and Engineering Technology (SCSET);2022-01