Semantic classification of bio-entities incorporating predicate-argument features

Kyung Mi Park, Hae-Chang Rim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose new external context features for the semantic classification of bio-entities. In the previous approaches, the words located on the left or the right context of bio-entities are frequently used as the external context features. However, in our prior experiments, the external contexts in a flat representation did not improve the performance. In this study, we incorporate predicate-argument features into training the ME-based classifier. Through parsing and argument identification, we recognize biomedical verbs that have argument relations with the constituents including a bio-entity, and then use the predicate-argument structures as the external context features. The extraction of predicateargument features can be done by performing two identification tasks: the biomedically salient word identification which determines whether a word is a biomedically salient word or not, and the target verb identification which identifies biomedical verbs that have argument relations with the constituents including a bio-entity. Experiments show that the performance of semantic classification in the bio domain can be improved by utilizing such predicate-argument features.

Original languageEnglish
Pages (from-to)1211-1214
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE91-D
Issue number4
DOIs
Publication statusPublished - 2008 Apr 1

Fingerprint

Semantics
Classifiers
Experiments

Keywords

  • Biomedical verb
  • Maximum entropy model
  • Predicate-argument feature
  • Semantic classification

ASJC Scopus subject areas

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

Cite this

Semantic classification of bio-entities incorporating predicate-argument features. / Park, Kyung Mi; Rim, Hae-Chang.

In: IEICE Transactions on Information and Systems, Vol. E91-D, No. 4, 01.04.2008, p. 1211-1214.

Research output: Contribution to journalArticle

@article{6b244498f3af485cab7aefa1eea0ab60,
title = "Semantic classification of bio-entities incorporating predicate-argument features",
abstract = "In this paper, we propose new external context features for the semantic classification of bio-entities. In the previous approaches, the words located on the left or the right context of bio-entities are frequently used as the external context features. However, in our prior experiments, the external contexts in a flat representation did not improve the performance. In this study, we incorporate predicate-argument features into training the ME-based classifier. Through parsing and argument identification, we recognize biomedical verbs that have argument relations with the constituents including a bio-entity, and then use the predicate-argument structures as the external context features. The extraction of predicateargument features can be done by performing two identification tasks: the biomedically salient word identification which determines whether a word is a biomedically salient word or not, and the target verb identification which identifies biomedical verbs that have argument relations with the constituents including a bio-entity. Experiments show that the performance of semantic classification in the bio domain can be improved by utilizing such predicate-argument features.",
keywords = "Biomedical verb, Maximum entropy model, Predicate-argument feature, Semantic classification",
author = "Park, {Kyung Mi} and Hae-Chang Rim",
year = "2008",
month = "4",
day = "1",
doi = "10.1093/ietisy/e91-d.4.1211",
language = "English",
volume = "E91-D",
pages = "1211--1214",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "4",

}

TY - JOUR

T1 - Semantic classification of bio-entities incorporating predicate-argument features

AU - Park, Kyung Mi

AU - Rim, Hae-Chang

PY - 2008/4/1

Y1 - 2008/4/1

N2 - In this paper, we propose new external context features for the semantic classification of bio-entities. In the previous approaches, the words located on the left or the right context of bio-entities are frequently used as the external context features. However, in our prior experiments, the external contexts in a flat representation did not improve the performance. In this study, we incorporate predicate-argument features into training the ME-based classifier. Through parsing and argument identification, we recognize biomedical verbs that have argument relations with the constituents including a bio-entity, and then use the predicate-argument structures as the external context features. The extraction of predicateargument features can be done by performing two identification tasks: the biomedically salient word identification which determines whether a word is a biomedically salient word or not, and the target verb identification which identifies biomedical verbs that have argument relations with the constituents including a bio-entity. Experiments show that the performance of semantic classification in the bio domain can be improved by utilizing such predicate-argument features.

AB - In this paper, we propose new external context features for the semantic classification of bio-entities. In the previous approaches, the words located on the left or the right context of bio-entities are frequently used as the external context features. However, in our prior experiments, the external contexts in a flat representation did not improve the performance. In this study, we incorporate predicate-argument features into training the ME-based classifier. Through parsing and argument identification, we recognize biomedical verbs that have argument relations with the constituents including a bio-entity, and then use the predicate-argument structures as the external context features. The extraction of predicateargument features can be done by performing two identification tasks: the biomedically salient word identification which determines whether a word is a biomedically salient word or not, and the target verb identification which identifies biomedical verbs that have argument relations with the constituents including a bio-entity. Experiments show that the performance of semantic classification in the bio domain can be improved by utilizing such predicate-argument features.

KW - Biomedical verb

KW - Maximum entropy model

KW - Predicate-argument feature

KW - Semantic classification

UR - http://www.scopus.com/inward/record.url?scp=68149169755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68149169755&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e91-d.4.1211

DO - 10.1093/ietisy/e91-d.4.1211

M3 - Article

VL - E91-D

SP - 1211

EP - 1214

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 4

ER -