Unsupervised gene function extraction using semantic vectors

Ehsan Emadzadeh; Azadeh Nikfarjam; Rachel E. Ginn; Graciela Gonzalez

doi:10.1093/database/bau084

Unsupervised gene function extraction using semantic vectors

Ehsan Emadzadeh, Azadeh Nikfarjam, Rachel E. Ginn, Graciela Gonzalez

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

1 Scopus citations

Abstract

UNLABELLED: Finding gene functions discussed in the literature is an important task of information extraction (IE) from biomedical documents. Automated computational methodologies can significantly reduce the need for manual curation and improve quality of other related IE systems. We propose an open-IE method for the BioCreative IV GO shared task (subtask b), focused on finding gene function terms [Gene Ontology (GO) terms] for different genes in an article. The proposed open-IE approach is based on distributional semantic similarity over the GO terms. The method does not require annotated data for training, which makes it highly generalizable. We achieve an F-measure of 0.26 on the test-set in the official submission for BioCreative-GO shared task, the third highest F-measure among the seven participants in the shared task.

DATABASE URL: https://code.google.com/p/rainbow-nlp/

Original language	English (US)
Journal	Database : the journal of biological databases and curation
Volume	2014
DOIs	https://doi.org/10.1093/database/bau084
State	Published - 2014

ASJC Scopus subject areas

Information Systems
General Biochemistry, Genetics and Molecular Biology
General Agricultural and Biological Sciences

Access to Document

10.1093/database/bau084

Cite this

@article{0f4d58929e044d0bb103169d8bc80295,

title = "Unsupervised gene function extraction using semantic vectors",

abstract = "UNLABELLED: Finding gene functions discussed in the literature is an important task of information extraction (IE) from biomedical documents. Automated computational methodologies can significantly reduce the need for manual curation and improve quality of other related IE systems. We propose an open-IE method for the BioCreative IV GO shared task (subtask b), focused on finding gene function terms [Gene Ontology (GO) terms] for different genes in an article. The proposed open-IE approach is based on distributional semantic similarity over the GO terms. The method does not require annotated data for training, which makes it highly generalizable. We achieve an F-measure of 0.26 on the test-set in the official submission for BioCreative-GO shared task, the third highest F-measure among the seven participants in the shared task.DATABASE URL: https://code.google.com/p/rainbow-nlp/",

author = "Ehsan Emadzadeh and Azadeh Nikfarjam and Ginn, {Rachel E.} and Graciela Gonzalez",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2014. Published by Oxford University Press.",

year = "2014",

doi = "10.1093/database/bau084",

language = "English (US)",

volume = "2014",

journal = "Database : the journal of biological databases and curation",

issn = "1758-0463",

publisher = "Oxford University Press",

}

TY - JOUR

T1 - Unsupervised gene function extraction using semantic vectors

AU - Emadzadeh, Ehsan

AU - Nikfarjam, Azadeh

AU - Ginn, Rachel E.

AU - Gonzalez, Graciela

PY - 2014

Y1 - 2014

N2 - UNLABELLED: Finding gene functions discussed in the literature is an important task of information extraction (IE) from biomedical documents. Automated computational methodologies can significantly reduce the need for manual curation and improve quality of other related IE systems. We propose an open-IE method for the BioCreative IV GO shared task (subtask b), focused on finding gene function terms [Gene Ontology (GO) terms] for different genes in an article. The proposed open-IE approach is based on distributional semantic similarity over the GO terms. The method does not require annotated data for training, which makes it highly generalizable. We achieve an F-measure of 0.26 on the test-set in the official submission for BioCreative-GO shared task, the third highest F-measure among the seven participants in the shared task.DATABASE URL: https://code.google.com/p/rainbow-nlp/

AB - UNLABELLED: Finding gene functions discussed in the literature is an important task of information extraction (IE) from biomedical documents. Automated computational methodologies can significantly reduce the need for manual curation and improve quality of other related IE systems. We propose an open-IE method for the BioCreative IV GO shared task (subtask b), focused on finding gene function terms [Gene Ontology (GO) terms] for different genes in an article. The proposed open-IE approach is based on distributional semantic similarity over the GO terms. The method does not require annotated data for training, which makes it highly generalizable. We achieve an F-measure of 0.26 on the test-set in the official submission for BioCreative-GO shared task, the third highest F-measure among the seven participants in the shared task.DATABASE URL: https://code.google.com/p/rainbow-nlp/

UR - http://www.scopus.com/inward/record.url?scp=84925545091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925545091&partnerID=8YFLogxK

U2 - 10.1093/database/bau084

DO - 10.1093/database/bau084

M3 - Article

C2 - 25209025

AN - SCOPUS:84925545091

SN - 1758-0463

VL - 2014

JO - Database : the journal of biological databases and curation

JF - Database : the journal of biological databases and curation

ER -

Unsupervised gene function extraction using semantic vectors

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this