Assessing semantic similarity between concepts using Wikipedia based on nonlinear fitting

Guangjian Huang, Yuncheng Jiang, Wenjun Ma, Weiru Liu

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

1 Citation (Scopus)
148 Downloads (Pure)

Abstract

Feature-based methods of semantic similarity with Wikipedia achieve fruitful performances on measuring the "likeness" between objects in many research fields. However, since Wikipedia is created and edited by volunteers around the world, the preciseness of these methods more or less are influenced by the incompleteness, invalidity and inconsistency of the knowledge in Wikipedia. Unfortunately, this problem has not got enough attention in the existing work. To address this issue, this paper proposes a novel feature-based method for semantic similarity, which has three parts: low frequency features removal, the similarities of generalized synonyms computing, and weighted feature-based methods based on nonlinear fitting. Moreover, we show that our new method can always get a better Pearson correlation coefficient on one or more benchmarks through a set of experimental evaluations.
Original languageEnglish
Title of host publicationThe 12th International Conference on Knowledge Science, Engineering and Management (KSEM 2019)
EditorsRandy Goebel, Yuzuru Tanaka, Wolfgang Wahlster
PublisherSpringer
Pages159-171
Number of pages13
ISBN (Electronic) 978-3-030-29563-9
ISBN (Print)978-3-030-29562-2
DOIs
Publication statusPublished - Aug 2019

Publication series

NameLecture Notes in Artificial Intelligence
PublisherSpringer
Volume11776
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Keywords

  • Semantic similarity
  • Wikipedia
  • Nonlinear fitting

Fingerprint

Dive into the research topics of 'Assessing semantic similarity between concepts using Wikipedia based on nonlinear fitting'. Together they form a unique fingerprint.

Cite this