Computing word semantic relatedness for question retrieval in community question answering

Jung Tae Lee, Young In Song, Hae-Chang Rim

Research output: Contribution to journalArticle

Abstract

Previous approaches to question retrieval in communitybased question answering rely on statistical translation techniques to match users' questions (queries) against collections of previously asked questions. This paper presents a simple but effective method for computing word relatedness to improve question retrieval based on word co-occurrence information directly extracted from question and answer archives. Experimental results show that the proposed approach significantly outperforms translation-based approaches.

Original languageEnglish
Pages (from-to)736-739
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE92-D
Issue number4
DOIs
Publication statusPublished - 2009 Dec 1

Fingerprint

Semantics

Keywords

  • Community question answering
  • Question retrieval
  • Word semantic relatedness

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Computing word semantic relatedness for question retrieval in community question answering. / Lee, Jung Tae; Song, Young In; Rim, Hae-Chang.

In: IEICE Transactions on Information and Systems, Vol. E92-D, No. 4, 01.12.2009, p. 736-739.

Research output: Contribution to journalArticle

@article{daadc7c0aa234d8eb242496a2d3f5248,
title = "Computing word semantic relatedness for question retrieval in community question answering",
abstract = "Previous approaches to question retrieval in communitybased question answering rely on statistical translation techniques to match users' questions (queries) against collections of previously asked questions. This paper presents a simple but effective method for computing word relatedness to improve question retrieval based on word co-occurrence information directly extracted from question and answer archives. Experimental results show that the proposed approach significantly outperforms translation-based approaches.",
keywords = "Community question answering, Question retrieval, Word semantic relatedness",
author = "Lee, {Jung Tae} and Song, {Young In} and Hae-Chang Rim",
year = "2009",
month = "12",
day = "1",
doi = "10.1587/transinf.E92.D.736",
language = "English",
volume = "E92-D",
pages = "736--739",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "4",

}

TY - JOUR

T1 - Computing word semantic relatedness for question retrieval in community question answering

AU - Lee, Jung Tae

AU - Song, Young In

AU - Rim, Hae-Chang

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Previous approaches to question retrieval in communitybased question answering rely on statistical translation techniques to match users' questions (queries) against collections of previously asked questions. This paper presents a simple but effective method for computing word relatedness to improve question retrieval based on word co-occurrence information directly extracted from question and answer archives. Experimental results show that the proposed approach significantly outperforms translation-based approaches.

AB - Previous approaches to question retrieval in communitybased question answering rely on statistical translation techniques to match users' questions (queries) against collections of previously asked questions. This paper presents a simple but effective method for computing word relatedness to improve question retrieval based on word co-occurrence information directly extracted from question and answer archives. Experimental results show that the proposed approach significantly outperforms translation-based approaches.

KW - Community question answering

KW - Question retrieval

KW - Word semantic relatedness

UR - http://www.scopus.com/inward/record.url?scp=77950358505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950358505&partnerID=8YFLogxK

U2 - 10.1587/transinf.E92.D.736

DO - 10.1587/transinf.E92.D.736

M3 - Article

AN - SCOPUS:77950358505

VL - E92-D

SP - 736

EP - 739

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 4

ER -