Extracting Inter-Sentence Relations for Associating Biological Context with Events in Biomedical Texts

Enrique Noriega-Atala; Paul D. Hein; Shraddha S. Thumsi; Zechy Wong; Xia Wang; Sean M. Hendryx; Clayton T. Morrison

doi:10.1109/TCBB.2019.2904231

Extracting Inter-Sentence Relations for Associating Biological Context with Events in Biomedical Texts

Enrique Noriega-Atala, Paul D. Hein, Shraddha S. Thumsi, Zechy Wong, Xia Wang, Sean M. Hendryx, Clayton T. Morrison

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

We present an analysis of the problem of identifying biological context and associating it with biochemical events described in biomedical texts. This constitutes a non-trivial, inter-sentential relation extraction task. We focus on biological context as descriptions of the species, tissue type, and cell type that are associated with biochemical events. We present a new corpus of open access biomedical texts that have been annotated by biology subject matter experts to highlight context-event relations. Using this corpus, we evaluate several classifiers for context-event association along with a detailed analysis of the impact of a variety of linguistic features on classifier performance. We find that gradient tree boosting performs by far the best, achieving an F1 of 0.865 in a cross-validation study.

Original language	English (US)
Article number	8664185
Pages (from-to)	1895-1906
Number of pages	12
Journal	IEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume	17
Issue number	6
DOIs	https://doi.org/10.1109/TCBB.2019.2904231
State	Published - Nov 1 2020

Keywords

Context
NLP
bioinformatics
data mining
inter-sentence relation extraction

ASJC Scopus subject areas

Biotechnology
Genetics
Applied Mathematics

Access to Document

10.1109/TCBB.2019.2904231

Cite this

@article{0ce0c2b709ab421292eaa68a8b30df2c,

title = "Extracting Inter-Sentence Relations for Associating Biological Context with Events in Biomedical Texts",

abstract = "We present an analysis of the problem of identifying biological context and associating it with biochemical events described in biomedical texts. This constitutes a non-trivial, inter-sentential relation extraction task. We focus on biological context as descriptions of the species, tissue type, and cell type that are associated with biochemical events. We present a new corpus of open access biomedical texts that have been annotated by biology subject matter experts to highlight context-event relations. Using this corpus, we evaluate several classifiers for context-event association along with a detailed analysis of the impact of a variety of linguistic features on classifier performance. We find that gradient tree boosting performs by far the best, achieving an F1 of 0.865 in a cross-validation study.",

keywords = "Context, NLP, bioinformatics, data mining, inter-sentence relation extraction",

author = "Enrique Noriega-Atala and Hein, {Paul D.} and Thumsi, {Shraddha S.} and Zechy Wong and Xia Wang and Hendryx, {Sean M.} and Morrison, {Clayton T.}",

note = "Funding Information: This work was supported by the Defense Advanced Research Projects Agency (DARPA) Big Mechanism [ARO W911NF-14-1-0395]. The authors also thank the University of Arizona Research High Performance Computing support team. Funding Information: 11. ... minus the empty feature set. 12. We greatfully acknowledge support from the University of Arizona Research High Performance Computing (HPC) facility. Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2020",

month = nov,

day = "1",

doi = "10.1109/TCBB.2019.2904231",

language = "English (US)",

volume = "17",

pages = "1895--1906",

journal = "IEEE/ACM Transactions on Computational Biology and Bioinformatics",

issn = "1545-5963",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "6",

}

TY - JOUR

T1 - Extracting Inter-Sentence Relations for Associating Biological Context with Events in Biomedical Texts

AU - Noriega-Atala, Enrique

AU - Hein, Paul D.

AU - Thumsi, Shraddha S.

AU - Wong, Zechy

AU - Wang, Xia

AU - Hendryx, Sean M.

AU - Morrison, Clayton T.

N1 - Funding Information: This work was supported by the Defense Advanced Research Projects Agency (DARPA) Big Mechanism [ARO W911NF-14-1-0395]. The authors also thank the University of Arizona Research High Performance Computing support team. Funding Information: 11. ... minus the empty feature set. 12. We greatfully acknowledge support from the University of Arizona Research High Performance Computing (HPC) facility. Publisher Copyright: © 2004-2012 IEEE.

PY - 2020/11/1

Y1 - 2020/11/1

N2 - We present an analysis of the problem of identifying biological context and associating it with biochemical events described in biomedical texts. This constitutes a non-trivial, inter-sentential relation extraction task. We focus on biological context as descriptions of the species, tissue type, and cell type that are associated with biochemical events. We present a new corpus of open access biomedical texts that have been annotated by biology subject matter experts to highlight context-event relations. Using this corpus, we evaluate several classifiers for context-event association along with a detailed analysis of the impact of a variety of linguistic features on classifier performance. We find that gradient tree boosting performs by far the best, achieving an F1 of 0.865 in a cross-validation study.

AB - We present an analysis of the problem of identifying biological context and associating it with biochemical events described in biomedical texts. This constitutes a non-trivial, inter-sentential relation extraction task. We focus on biological context as descriptions of the species, tissue type, and cell type that are associated with biochemical events. We present a new corpus of open access biomedical texts that have been annotated by biology subject matter experts to highlight context-event relations. Using this corpus, we evaluate several classifiers for context-event association along with a detailed analysis of the impact of a variety of linguistic features on classifier performance. We find that gradient tree boosting performs by far the best, achieving an F1 of 0.865 in a cross-validation study.

KW - Context

KW - NLP

KW - bioinformatics

KW - data mining

KW - inter-sentence relation extraction

UR - http://www.scopus.com/inward/record.url?scp=85097514823&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85097514823&partnerID=8YFLogxK

U2 - 10.1109/TCBB.2019.2904231

DO - 10.1109/TCBB.2019.2904231

M3 - Article

C2 - 30869629

AN - SCOPUS:85097514823

SN - 1545-5963

VL - 17

SP - 1895

EP - 1906

JO - IEEE/ACM Transactions on Computational Biology and Bioinformatics

JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics

IS - 6

M1 - 8664185

ER -

Extracting Inter-Sentence Relations for Associating Biological Context with Events in Biomedical Texts

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this