Filling preposition-based templates to capture information from medical abstracts.

Research output: Chapter in Book/Report/Conference proceedingChapter

45 Citations (Scopus)

Abstract

Due to the recent explosion of information in the biomedical field, it is hard for a single researcher to review the complex network involving genes, proteins, and interactions. We are currently building GeneScene, a toolkit that will assist researchers in reviewing existing literature, and report on the first phase in our development effort: extracting the relevant information from medical abstracts. We are developing a medical parser that extracts information, fills basic prepositional-based templates, and combines the templates to capture the underlying sentence logic. We tested our parser on 50 unseen abstracts and found that it extracted 246 templates with a precision of 70%. In comparison with many other techniques, more information was extracted without sacrificing precision. Future improvement in precision will be achieved by correcting three categories of errors.

Original languageEnglish (US)
Title of host publicationPacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
Pages350-361
Number of pages12
StatePublished - 2002

Fingerprint

Research Personnel
Explosions
Proteins

Cite this

Leroy, G. A., & Chen, H. (2002). Filling preposition-based templates to capture information from medical abstracts. In Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing (pp. 350-361)

Filling preposition-based templates to capture information from medical abstracts. / Leroy, Gondy Augusta; Chen, Hsinchun.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. 2002. p. 350-361.

Research output: Chapter in Book/Report/Conference proceedingChapter

Leroy, GA & Chen, H 2002, Filling preposition-based templates to capture information from medical abstracts. in Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. pp. 350-361.
Leroy GA, Chen H. Filling preposition-based templates to capture information from medical abstracts. In Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. 2002. p. 350-361
Leroy, Gondy Augusta ; Chen, Hsinchun. / Filling preposition-based templates to capture information from medical abstracts. Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. 2002. pp. 350-361
@inbook{0d44a1b16c4c4a1691f718c860eec400,
title = "Filling preposition-based templates to capture information from medical abstracts.",
abstract = "Due to the recent explosion of information in the biomedical field, it is hard for a single researcher to review the complex network involving genes, proteins, and interactions. We are currently building GeneScene, a toolkit that will assist researchers in reviewing existing literature, and report on the first phase in our development effort: extracting the relevant information from medical abstracts. We are developing a medical parser that extracts information, fills basic prepositional-based templates, and combines the templates to capture the underlying sentence logic. We tested our parser on 50 unseen abstracts and found that it extracted 246 templates with a precision of 70{\%}. In comparison with many other techniques, more information was extracted without sacrificing precision. Future improvement in precision will be achieved by correcting three categories of errors.",
author = "Leroy, {Gondy Augusta} and Hsinchun Chen",
year = "2002",
language = "English (US)",
pages = "350--361",
booktitle = "Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing",

}

TY - CHAP

T1 - Filling preposition-based templates to capture information from medical abstracts.

AU - Leroy, Gondy Augusta

AU - Chen, Hsinchun

PY - 2002

Y1 - 2002

N2 - Due to the recent explosion of information in the biomedical field, it is hard for a single researcher to review the complex network involving genes, proteins, and interactions. We are currently building GeneScene, a toolkit that will assist researchers in reviewing existing literature, and report on the first phase in our development effort: extracting the relevant information from medical abstracts. We are developing a medical parser that extracts information, fills basic prepositional-based templates, and combines the templates to capture the underlying sentence logic. We tested our parser on 50 unseen abstracts and found that it extracted 246 templates with a precision of 70%. In comparison with many other techniques, more information was extracted without sacrificing precision. Future improvement in precision will be achieved by correcting three categories of errors.

AB - Due to the recent explosion of information in the biomedical field, it is hard for a single researcher to review the complex network involving genes, proteins, and interactions. We are currently building GeneScene, a toolkit that will assist researchers in reviewing existing literature, and report on the first phase in our development effort: extracting the relevant information from medical abstracts. We are developing a medical parser that extracts information, fills basic prepositional-based templates, and combines the templates to capture the underlying sentence logic. We tested our parser on 50 unseen abstracts and found that it extracted 246 templates with a precision of 70%. In comparison with many other techniques, more information was extracted without sacrificing precision. Future improvement in precision will be achieved by correcting three categories of errors.

UR - http://www.scopus.com/inward/record.url?scp=0036371839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036371839&partnerID=8YFLogxK

M3 - Chapter

C2 - 11928489

AN - SCOPUS:0036371839

SP - 350

EP - 361

BT - Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

ER -