Exploiting background knowledge for relation extraction

Yee Seng Chan, Dan Roth

Research output: Contribution to conferencePaper

Abstract

Relation extraction is the task of recognizing semantic relations among entities. Given a particular sentence supervised approaches to Relation Extraction employed feature or kernel functions which usually have a single sentence in their scope. The overall aim of this paper is to propose methods for using knowledge and resources that are external to the target sentence, as a way to improve relation extraction. We demonstrate this by exploiting background knowledge such as relationships among the target relations, as well as by considering how target relations relate to some existing knowledge resources. Our methods are general and we suggest that some of them could be applied to other NLP tasks.

Original languageEnglish (US)
Pages152-160
Number of pages9
StatePublished - Dec 1 2010
Event23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China
Duration: Aug 23 2010Aug 27 2010

Other

Other23rd International Conference on Computational Linguistics, Coling 2010
CountryChina
CityBeijing
Period8/23/108/27/10

Fingerprint

Feature extraction
Semantics
resources
semantics
knowledge
Background Knowledge
Resources
Kernel
Natural Language Processing
Feature Extraction
Entity
Semantic Relations

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Cite this

Chan, Y. S., & Roth, D. (2010). Exploiting background knowledge for relation extraction. 152-160. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.

Exploiting background knowledge for relation extraction. / Chan, Yee Seng; Roth, Dan.

2010. 152-160 Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.

Research output: Contribution to conferencePaper

Chan, YS & Roth, D 2010, 'Exploiting background knowledge for relation extraction', Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China, 8/23/10 - 8/27/10 pp. 152-160.
Chan YS, Roth D. Exploiting background knowledge for relation extraction. 2010. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.
Chan, Yee Seng ; Roth, Dan. / Exploiting background knowledge for relation extraction. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.9 p.
@conference{7d2c78a257ee4cd89c1c83029b5cd689,
title = "Exploiting background knowledge for relation extraction",
abstract = "Relation extraction is the task of recognizing semantic relations among entities. Given a particular sentence supervised approaches to Relation Extraction employed feature or kernel functions which usually have a single sentence in their scope. The overall aim of this paper is to propose methods for using knowledge and resources that are external to the target sentence, as a way to improve relation extraction. We demonstrate this by exploiting background knowledge such as relationships among the target relations, as well as by considering how target relations relate to some existing knowledge resources. Our methods are general and we suggest that some of them could be applied to other NLP tasks.",
author = "Chan, {Yee Seng} and Dan Roth",
year = "2010",
month = "12",
day = "1",
language = "English (US)",
pages = "152--160",
note = "23rd International Conference on Computational Linguistics, Coling 2010 ; Conference date: 23-08-2010 Through 27-08-2010",

}

TY - CONF

T1 - Exploiting background knowledge for relation extraction

AU - Chan, Yee Seng

AU - Roth, Dan

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Relation extraction is the task of recognizing semantic relations among entities. Given a particular sentence supervised approaches to Relation Extraction employed feature or kernel functions which usually have a single sentence in their scope. The overall aim of this paper is to propose methods for using knowledge and resources that are external to the target sentence, as a way to improve relation extraction. We demonstrate this by exploiting background knowledge such as relationships among the target relations, as well as by considering how target relations relate to some existing knowledge resources. Our methods are general and we suggest that some of them could be applied to other NLP tasks.

AB - Relation extraction is the task of recognizing semantic relations among entities. Given a particular sentence supervised approaches to Relation Extraction employed feature or kernel functions which usually have a single sentence in their scope. The overall aim of this paper is to propose methods for using knowledge and resources that are external to the target sentence, as a way to improve relation extraction. We demonstrate this by exploiting background knowledge such as relationships among the target relations, as well as by considering how target relations relate to some existing knowledge resources. Our methods are general and we suggest that some of them could be applied to other NLP tasks.

UR - http://www.scopus.com/inward/record.url?scp=80053253822&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053253822&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:80053253822

SP - 152

EP - 160

ER -