Unsupervised event extraction from biomedical literature using co-occurrence information and basic patterns

Hong W. Chun, Young Sook Hwang, Hae-Chang Rim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In this paper, we propose a new unsupervised method of extracting events from biomedical literature, which uses the score measures of events and patterns having reciprocal effects on each other. We, first, generate candidate events by performing linguistic preprocessing and utilizing basic event pattern information, and then extract reliable events based on the event score which is estimated by using co-occurrence information of candidate event's arguments and pattern score. Unlike the previous approaches, the proposed approach does not require a huge number of rules and manually constructed training corpora. Experimental results on GENIA corpora show that the proposed method can achieve high recall (69.7%) as well as high precision (90.3%).

Original languageEnglish
Title of host publicationLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
EditorsK.-Y. Su, J. Tsujii, J.-H. Lee, O.Y. Kwong
Pages777-786
Number of pages10
Volume3248
Publication statusPublished - 2005
EventFirst International Joint Conference on Natural Language Processing - IJCNLP 2004 - Hainan Island, China
Duration: 2004 Mar 222004 Mar 24

Other

OtherFirst International Joint Conference on Natural Language Processing - IJCNLP 2004
CountryChina
CityHainan Island
Period04/3/2204/3/24

Fingerprint

Linguistics

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Chun, H. W., Hwang, Y. S., & Rim, H-C. (2005). Unsupervised event extraction from biomedical literature using co-occurrence information and basic patterns. In K-Y. Su, J. Tsujii, J-H. Lee, & O. Y. Kwong (Eds.), Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3248, pp. 777-786)

Unsupervised event extraction from biomedical literature using co-occurrence information and basic patterns. / Chun, Hong W.; Hwang, Young Sook; Rim, Hae-Chang.

Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). ed. / K.-Y. Su; J. Tsujii; J.-H. Lee; O.Y. Kwong. Vol. 3248 2005. p. 777-786.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chun, HW, Hwang, YS & Rim, H-C 2005, Unsupervised event extraction from biomedical literature using co-occurrence information and basic patterns. in K-Y Su, J Tsujii, J-H Lee & OY Kwong (eds), Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). vol. 3248, pp. 777-786, First International Joint Conference on Natural Language Processing - IJCNLP 2004, Hainan Island, China, 04/3/22.
Chun HW, Hwang YS, Rim H-C. Unsupervised event extraction from biomedical literature using co-occurrence information and basic patterns. In Su K-Y, Tsujii J, Lee J-H, Kwong OY, editors, Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). Vol. 3248. 2005. p. 777-786
Chun, Hong W. ; Hwang, Young Sook ; Rim, Hae-Chang. / Unsupervised event extraction from biomedical literature using co-occurrence information and basic patterns. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). editor / K.-Y. Su ; J. Tsujii ; J.-H. Lee ; O.Y. Kwong. Vol. 3248 2005. pp. 777-786
@inproceedings{d671901092984f949276ee0ef5785e2a,
title = "Unsupervised event extraction from biomedical literature using co-occurrence information and basic patterns",
abstract = "In this paper, we propose a new unsupervised method of extracting events from biomedical literature, which uses the score measures of events and patterns having reciprocal effects on each other. We, first, generate candidate events by performing linguistic preprocessing and utilizing basic event pattern information, and then extract reliable events based on the event score which is estimated by using co-occurrence information of candidate event's arguments and pattern score. Unlike the previous approaches, the proposed approach does not require a huge number of rules and manually constructed training corpora. Experimental results on GENIA corpora show that the proposed method can achieve high recall (69.7{\%}) as well as high precision (90.3{\%}).",
author = "Chun, {Hong W.} and Hwang, {Young Sook} and Hae-Chang Rim",
year = "2005",
language = "English",
volume = "3248",
pages = "777--786",
editor = "K.-Y. Su and J. Tsujii and J.-H. Lee and O.Y. Kwong",
booktitle = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

}

TY - GEN

T1 - Unsupervised event extraction from biomedical literature using co-occurrence information and basic patterns

AU - Chun, Hong W.

AU - Hwang, Young Sook

AU - Rim, Hae-Chang

PY - 2005

Y1 - 2005

N2 - In this paper, we propose a new unsupervised method of extracting events from biomedical literature, which uses the score measures of events and patterns having reciprocal effects on each other. We, first, generate candidate events by performing linguistic preprocessing and utilizing basic event pattern information, and then extract reliable events based on the event score which is estimated by using co-occurrence information of candidate event's arguments and pattern score. Unlike the previous approaches, the proposed approach does not require a huge number of rules and manually constructed training corpora. Experimental results on GENIA corpora show that the proposed method can achieve high recall (69.7%) as well as high precision (90.3%).

AB - In this paper, we propose a new unsupervised method of extracting events from biomedical literature, which uses the score measures of events and patterns having reciprocal effects on each other. We, first, generate candidate events by performing linguistic preprocessing and utilizing basic event pattern information, and then extract reliable events based on the event score which is estimated by using co-occurrence information of candidate event's arguments and pattern score. Unlike the previous approaches, the proposed approach does not require a huge number of rules and manually constructed training corpora. Experimental results on GENIA corpora show that the proposed method can achieve high recall (69.7%) as well as high precision (90.3%).

UR - http://www.scopus.com/inward/record.url?scp=26444589669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444589669&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:26444589669

VL - 3248

SP - 777

EP - 786

BT - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

A2 - Su, K.-Y.

A2 - Tsujii, J.

A2 - Lee, J.-H.

A2 - Kwong, O.Y.

ER -