A study of using syntactic cues in short-text similarity measure

Po Sen Huang, Po Sheng Chiu, Jia Wei Chang, Yueh-Min Huang, Ming Che Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Short-text semantic similarity is an essential technique of natural language search and is widely used in social network analysis and opinion mining to find unknown knowledge. Such similarity measures usually measure short texts with 10-20 words. Similar to spoken utterances, short texts do not necessarily follow formal grammatical rules. The limited information contained in short texts and their syntactic and semantic flexibility make similarity measures difficult. Therefore, this study designed and tested a part-of-speech-based short-text similarity algorithm to solve those problems. The effects of evaluating different parts of speech are thoroughly discussed. The proposed algorithm achieved the best performance using word measures corresponding to different parts of speech.

Original languageEnglish
Pages (from-to)839-850
Number of pages12
JournalJournal of Internet Technology
Volume20
Issue number3
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Syntactics
Semantics
Electric network analysis

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Networks and Communications

Cite this

Huang, Po Sen ; Chiu, Po Sheng ; Chang, Jia Wei ; Huang, Yueh-Min ; Lee, Ming Che. / A study of using syntactic cues in short-text similarity measure. In: Journal of Internet Technology. 2019 ; Vol. 20, No. 3. pp. 839-850.
@article{cdbcc9f152794e1db0456132273c35da,
title = "A study of using syntactic cues in short-text similarity measure",
abstract = "Short-text semantic similarity is an essential technique of natural language search and is widely used in social network analysis and opinion mining to find unknown knowledge. Such similarity measures usually measure short texts with 10-20 words. Similar to spoken utterances, short texts do not necessarily follow formal grammatical rules. The limited information contained in short texts and their syntactic and semantic flexibility make similarity measures difficult. Therefore, this study designed and tested a part-of-speech-based short-text similarity algorithm to solve those problems. The effects of evaluating different parts of speech are thoroughly discussed. The proposed algorithm achieved the best performance using word measures corresponding to different parts of speech.",
author = "Huang, {Po Sen} and Chiu, {Po Sheng} and Chang, {Jia Wei} and Yueh-Min Huang and Lee, {Ming Che}",
year = "2019",
month = "1",
day = "1",
doi = "10.3966/160792642019052003017",
language = "English",
volume = "20",
pages = "839--850",
journal = "Journal of Internet Technology",
issn = "1607-9264",
publisher = "Taiwan Academic Network Management Committee",
number = "3",

}

A study of using syntactic cues in short-text similarity measure. / Huang, Po Sen; Chiu, Po Sheng; Chang, Jia Wei; Huang, Yueh-Min; Lee, Ming Che.

In: Journal of Internet Technology, Vol. 20, No. 3, 01.01.2019, p. 839-850.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A study of using syntactic cues in short-text similarity measure

AU - Huang, Po Sen

AU - Chiu, Po Sheng

AU - Chang, Jia Wei

AU - Huang, Yueh-Min

AU - Lee, Ming Che

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Short-text semantic similarity is an essential technique of natural language search and is widely used in social network analysis and opinion mining to find unknown knowledge. Such similarity measures usually measure short texts with 10-20 words. Similar to spoken utterances, short texts do not necessarily follow formal grammatical rules. The limited information contained in short texts and their syntactic and semantic flexibility make similarity measures difficult. Therefore, this study designed and tested a part-of-speech-based short-text similarity algorithm to solve those problems. The effects of evaluating different parts of speech are thoroughly discussed. The proposed algorithm achieved the best performance using word measures corresponding to different parts of speech.

AB - Short-text semantic similarity is an essential technique of natural language search and is widely used in social network analysis and opinion mining to find unknown knowledge. Such similarity measures usually measure short texts with 10-20 words. Similar to spoken utterances, short texts do not necessarily follow formal grammatical rules. The limited information contained in short texts and their syntactic and semantic flexibility make similarity measures difficult. Therefore, this study designed and tested a part-of-speech-based short-text similarity algorithm to solve those problems. The effects of evaluating different parts of speech are thoroughly discussed. The proposed algorithm achieved the best performance using word measures corresponding to different parts of speech.

UR - http://www.scopus.com/inward/record.url?scp=85070998563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070998563&partnerID=8YFLogxK

U2 - 10.3966/160792642019052003017

DO - 10.3966/160792642019052003017

M3 - Article

AN - SCOPUS:85070998563

VL - 20

SP - 839

EP - 850

JO - Journal of Internet Technology

JF - Journal of Internet Technology

SN - 1607-9264

IS - 3

ER -