Verifying person descriptions with term-entity association

Su Jian Li; Wenjie Li; Qin Lu; Rui Feng Xu

Verifying person descriptions with term-entity association

Su Jian Li, Wenjie Li, Qin Lu, Rui Feng Xu

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

Person description extraction is an important task in biography generation, question answering and summarization, etc. While most of the previous extraction methods mainly depended on structural information, the work presented in the paper will focus on extraction verification by integrating linguistic knowledge provided by HowNet (with semantic knowledge) and the newswire corpus (with statistical information), from which the associations between terms (i.e. the words in HowNet) and person entities are measured. With Term-Entity association, ineligible descriptions extracted could be filtered out, and a higher precision is achieved in turn.

Original language	English
Title of host publication	2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005
Pages	50-56
Number of pages	7
Publication status	Published - 12 Dec 2005
Event	International Conference on Machine Learning and Cybernetics, ICMLC 2005 - Guangzhou, China Duration: 18 Aug 2005 → 21 Aug 2005

Conference

Conference	International Conference on Machine Learning and Cybernetics, ICMLC 2005
Country/Territory	China
City	Guangzhou
Period	18/08/05 → 21/08/05

Keywords

Description
Information extraction
Natural language processing
Term-entity association

ASJC Scopus subject areas

General Engineering

Cite this

@inproceedings{d0ffb10b174742fdaac960dac27b03e9,

title = "Verifying person descriptions with term-entity association",

abstract = "Person description extraction is an important task in biography generation, question answering and summarization, etc. While most of the previous extraction methods mainly depended on structural information, the work presented in the paper will focus on extraction verification by integrating linguistic knowledge provided by HowNet (with semantic knowledge) and the newswire corpus (with statistical information), from which the associations between terms (i.e. the words in HowNet) and person entities are measured. With Term-Entity association, ineligible descriptions extracted could be filtered out, and a higher precision is achieved in turn.",

keywords = "Description, Information extraction, Natural language processing, Term-entity association",

author = "Li, {Su Jian} and Wenjie Li and Qin Lu and Xu, {Rui Feng}",

year = "2005",

month = dec,

day = "12",

language = "English",

isbn = "078039092X",

pages = "50--56",

booktitle = "2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005",

note = "International Conference on Machine Learning and Cybernetics, ICMLC 2005 ; Conference date: 18-08-2005 Through 21-08-2005",

}

TY - GEN

T1 - Verifying person descriptions with term-entity association

AU - Li, Su Jian

AU - Li, Wenjie

AU - Lu, Qin

AU - Xu, Rui Feng

PY - 2005/12/12

Y1 - 2005/12/12

N2 - Person description extraction is an important task in biography generation, question answering and summarization, etc. While most of the previous extraction methods mainly depended on structural information, the work presented in the paper will focus on extraction verification by integrating linguistic knowledge provided by HowNet (with semantic knowledge) and the newswire corpus (with statistical information), from which the associations between terms (i.e. the words in HowNet) and person entities are measured. With Term-Entity association, ineligible descriptions extracted could be filtered out, and a higher precision is achieved in turn.

AB - Person description extraction is an important task in biography generation, question answering and summarization, etc. While most of the previous extraction methods mainly depended on structural information, the work presented in the paper will focus on extraction verification by integrating linguistic knowledge provided by HowNet (with semantic knowledge) and the newswire corpus (with statistical information), from which the associations between terms (i.e. the words in HowNet) and person entities are measured. With Term-Entity association, ineligible descriptions extracted could be filtered out, and a higher precision is achieved in turn.

KW - Description

KW - Information extraction

KW - Natural language processing

KW - Term-entity association

UR - http://www.scopus.com/inward/record.url?scp=28444469262&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 078039092X

SN - 9780780390928

SP - 50

EP - 56

BT - 2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005

T2 - International Conference on Machine Learning and Cybernetics, ICMLC 2005

Y2 - 18 August 2005 through 21 August 2005

ER -

Verifying person descriptions with term-entity association

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this