Event frame extraction based on a gene regulation corpus

Yutaka Sasaki; Paul Thompson; Philip Cotter; John McNaught; Sophia Ananiadou

Event frame extraction based on a gene regulation corpus

Yutaka Sasaki, Paul Thompson, Philip Cotter, John McNaught, Sophia Ananiadou

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper describes the supervised acquisition of semantic event frames based on a corpus of biomedical abstracts, in which the biological process of E. coli gene regulation has been linguistically annotated by a group of biologists in the EC research project "BOOTStrep". Gene regulation is one of the rapidly advancing areas for which information extraction could boost research. Event frames are an essential linguistic resource for extraction
of information from biological literature. This paper presents a specification for linguistic-level annotation of gene regulation events, followed by novel methods of automatic event frame extraction from text. The event frame extraction performance has been evaluated with 10-fold cross validation. The experimental results show that a precision of nearly 50% and a recall of around 20% are achieved. Since the goal of this paper is event frame extraction, rather than event instance extraction, the issue of low recall could be solved by applying the methods to a larger-scale corpus.

Original language	English
Pages	761-768
Publication status	Published - 2008
Event	22nd International Conference on Computational Linguistics, Coling 2008 - Manchester Duration: 1 Jul 2008 → … http://www.aclweb.org/anthology/C08-1035

Conference

Conference	22nd International Conference on Computational Linguistics, Coling 2008
City	Manchester
Period	1/07/08 → …
Internet address	http://www.aclweb.org/anthology/C08-1035

Access to Document

http://aclweb.org/anthology/C08-1096Licence: CC BY-NC-SA

Cite this

@conference{70c53b33a3e64117adb30f3e8fb124e0,

title = "Event frame extraction based on a gene regulation corpus",

abstract = "This paper describes the supervised acquisition of semantic event frames based on a corpus of biomedical abstracts, in which the biological process of E. coli gene regulation has been linguistically annotated by a group of biologists in the EC research project {"}BOOTStrep{"}. Gene regulation is one of the rapidly advancing areas for which information extraction could boost research. Event frames are an essential linguistic resource for extraction of information from biological literature. This paper presents a specification for linguistic-level annotation of gene regulation events, followed by novel methods of automatic event frame extraction from text. The event frame extraction performance has been evaluated with 10-fold cross validation. The experimental results show that a precision of nearly 50% and a recall of around 20% are achieved. Since the goal of this paper is event frame extraction, rather than event instance extraction, the issue of low recall could be solved by applying the methods to a larger-scale corpus.",

author = "Yutaka Sasaki and Paul Thompson and Philip Cotter and John McNaught and Sophia Ananiadou",

year = "2008",

language = "English",

pages = "761--768",

note = "22nd International Conference on Computational Linguistics, Coling 2008 ; Conference date: 01-07-2008",

url = "http://www.aclweb.org/anthology/C08-1035",

}

TY - CONF

T1 - Event frame extraction based on a gene regulation corpus

AU - Sasaki, Yutaka

AU - Thompson, Paul

AU - Cotter, Philip

AU - McNaught, John

AU - Ananiadou, Sophia

PY - 2008

Y1 - 2008

N2 - This paper describes the supervised acquisition of semantic event frames based on a corpus of biomedical abstracts, in which the biological process of E. coli gene regulation has been linguistically annotated by a group of biologists in the EC research project "BOOTStrep". Gene regulation is one of the rapidly advancing areas for which information extraction could boost research. Event frames are an essential linguistic resource for extraction of information from biological literature. This paper presents a specification for linguistic-level annotation of gene regulation events, followed by novel methods of automatic event frame extraction from text. The event frame extraction performance has been evaluated with 10-fold cross validation. The experimental results show that a precision of nearly 50% and a recall of around 20% are achieved. Since the goal of this paper is event frame extraction, rather than event instance extraction, the issue of low recall could be solved by applying the methods to a larger-scale corpus.

AB - This paper describes the supervised acquisition of semantic event frames based on a corpus of biomedical abstracts, in which the biological process of E. coli gene regulation has been linguistically annotated by a group of biologists in the EC research project "BOOTStrep". Gene regulation is one of the rapidly advancing areas for which information extraction could boost research. Event frames are an essential linguistic resource for extraction of information from biological literature. This paper presents a specification for linguistic-level annotation of gene regulation events, followed by novel methods of automatic event frame extraction from text. The event frame extraction performance has been evaluated with 10-fold cross validation. The experimental results show that a precision of nearly 50% and a recall of around 20% are achieved. Since the goal of this paper is event frame extraction, rather than event instance extraction, the issue of low recall could be solved by applying the methods to a larger-scale corpus.

M3 - Paper

SP - 761

EP - 768

T2 - 22nd International Conference on Computational Linguistics, Coling 2008

Y2 - 1 July 2008

ER -

Event frame extraction based on a gene regulation corpus

Abstract

Conference

Access to Document

Fingerprint

Cite this