Genomic information retrieval through selective extraction and tagging by the ASU-BioAI group

Lian Yu; Syed Toufeeq Ahmed; Graciela Gonzalez; Brandon Logsdon; Mutsumi Nakamura; Shawn Nikkila; Kalpesh Shah; Luis Tari; Ryan Wendt; Amanda Zeigler; Chitta Baral

Genomic information retrieval through selective extraction and tagging by the ASU-BioAI group

Lian Yu, Syed Toufeeq Ahmed, Graciela Gonzalez, Brandon Logsdon, Mutsumi Nakamura, Shawn Nikkila, Kalpesh Shah, Luis Tari, Ryan Wendt, Amanda Zeigler, Chitta Baral

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we describe the approach used by the Arizona State University BioAI group for the ad-hoc retrieval task of the TREC Genomics Track 2005. We pre-process TREC query expression by adding the synonyms of genes, diseases, bio-processes, functions of organs, and selectively adding stemming verbs, nouns, and Mesh Heading categories. The pre-processed queries are used to perform initial search on the TREC Genomics collection of MEDLINE abstracts and produce a set of target abstracts using Apache Lucene. Tagging, anaphor resolution and fact extraction are performed on the target abstracts to refine the search results in terms of relevance. Finally, we rank the target abstracts according to the extracted facts, distance between terms and terms appeared in the query.

Original language	English (US)
Title of host publication	NIST Special Publication
State	Published - 2005
Event	14th Text REtrieval Conference, TREC 2005 - Gaithersburg, MD, United States Duration: Nov 15 2005 → Nov 18 2005

Other

Other	14th Text REtrieval Conference, TREC 2005
Country/Territory	United States
City	Gaithersburg, MD
Period	11/15/05 → 11/18/05

ASJC Scopus subject areas

Engineering(all)

Cite this

@inproceedings{1dd9b5b3d5f74358810231a4e2911c3b,

title = "Genomic information retrieval through selective extraction and tagging by the ASU-BioAI group",

abstract = "In this paper we describe the approach used by the Arizona State University BioAI group for the ad-hoc retrieval task of the TREC Genomics Track 2005. We pre-process TREC query expression by adding the synonyms of genes, diseases, bio-processes, functions of organs, and selectively adding stemming verbs, nouns, and Mesh Heading categories. The pre-processed queries are used to perform initial search on the TREC Genomics collection of MEDLINE abstracts and produce a set of target abstracts using Apache Lucene. Tagging, anaphor resolution and fact extraction are performed on the target abstracts to refine the search results in terms of relevance. Finally, we rank the target abstracts according to the extracted facts, distance between terms and terms appeared in the query.",

author = "Lian Yu and Ahmed, {Syed Toufeeq} and Graciela Gonzalez and Brandon Logsdon and Mutsumi Nakamura and Shawn Nikkila and Kalpesh Shah and Luis Tari and Ryan Wendt and Amanda Zeigler and Chitta Baral",

year = "2005",

language = "English (US)",

booktitle = "NIST Special Publication",

note = "14th Text REtrieval Conference, TREC 2005 ; Conference date: 15-11-2005 Through 18-11-2005",

}

TY - GEN

T1 - Genomic information retrieval through selective extraction and tagging by the ASU-BioAI group

AU - Yu, Lian

AU - Ahmed, Syed Toufeeq

AU - Gonzalez, Graciela

AU - Logsdon, Brandon

AU - Nakamura, Mutsumi

AU - Nikkila, Shawn

AU - Shah, Kalpesh

AU - Tari, Luis

AU - Wendt, Ryan

AU - Zeigler, Amanda

AU - Baral, Chitta

PY - 2005

Y1 - 2005

N2 - In this paper we describe the approach used by the Arizona State University BioAI group for the ad-hoc retrieval task of the TREC Genomics Track 2005. We pre-process TREC query expression by adding the synonyms of genes, diseases, bio-processes, functions of organs, and selectively adding stemming verbs, nouns, and Mesh Heading categories. The pre-processed queries are used to perform initial search on the TREC Genomics collection of MEDLINE abstracts and produce a set of target abstracts using Apache Lucene. Tagging, anaphor resolution and fact extraction are performed on the target abstracts to refine the search results in terms of relevance. Finally, we rank the target abstracts according to the extracted facts, distance between terms and terms appeared in the query.

AB - In this paper we describe the approach used by the Arizona State University BioAI group for the ad-hoc retrieval task of the TREC Genomics Track 2005. We pre-process TREC query expression by adding the synonyms of genes, diseases, bio-processes, functions of organs, and selectively adding stemming verbs, nouns, and Mesh Heading categories. The pre-processed queries are used to perform initial search on the TREC Genomics collection of MEDLINE abstracts and produce a set of target abstracts using Apache Lucene. Tagging, anaphor resolution and fact extraction are performed on the target abstracts to refine the search results in terms of relevance. Finally, we rank the target abstracts according to the extracted facts, distance between terms and terms appeared in the query.

UR - http://www.scopus.com/inward/record.url?scp=84873550675&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873550675&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84873550675

BT - NIST Special Publication

T2 - 14th Text REtrieval Conference, TREC 2005

Y2 - 15 November 2005 through 18 November 2005

ER -

Genomic information retrieval through selective extraction and tagging by the ASU-BioAI group

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this