The OHSU biomedical question answering system framework

Aaron Cohen, J. Yang, S. Fisher, B. Roark, William (Bill) Hersh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The Oregon Health & Science University submission to the TREC 2007 Genomics Track approached the entity list question answering task using a modular object oriented system framework. A system object coordinates a collection of processing objects into a pipe that constructs a set of queries, retrieves passage, and then processes those passages into a final output answer set. Using the framework we applied multiple levels of synonym expansion and a ranked series of topic queries with a range of specificities in order to retrieve all of the likely relevant passages with the most likely ranked higher. We then applied sentence pruning to the head and tail of each passage using both NLP and term-based techniques. Overall scores finished around the TREC Genomics mean for each of the four measures. Careful passage retrieval, including synonym expansion and multiple query construction, as well as sentence pruning was essential in achieving acceptable performance on this task.

Original languageEnglish (US)
Title of host publicationNIST Special Publication
StatePublished - 2007
Event16th Text REtrieval Conference, TREC 2007 - Gaithersburg, MD, United States
Duration: Nov 6 2007Nov 9 2007

Other

Other16th Text REtrieval Conference, TREC 2007
CountryUnited States
CityGaithersburg, MD
Period11/6/0711/9/07

Fingerprint

Pipe
Health
Processing
Genomics

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Cohen, A., Yang, J., Fisher, S., Roark, B., & Hersh, W. B. (2007). The OHSU biomedical question answering system framework. In NIST Special Publication

The OHSU biomedical question answering system framework. / Cohen, Aaron; Yang, J.; Fisher, S.; Roark, B.; Hersh, William (Bill).

NIST Special Publication. 2007.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cohen, A, Yang, J, Fisher, S, Roark, B & Hersh, WB 2007, The OHSU biomedical question answering system framework. in NIST Special Publication. 16th Text REtrieval Conference, TREC 2007, Gaithersburg, MD, United States, 11/6/07.
Cohen A, Yang J, Fisher S, Roark B, Hersh WB. The OHSU biomedical question answering system framework. In NIST Special Publication. 2007
Cohen, Aaron ; Yang, J. ; Fisher, S. ; Roark, B. ; Hersh, William (Bill). / The OHSU biomedical question answering system framework. NIST Special Publication. 2007.
@inproceedings{e9b144a6e2db4069bb5f50a382d0dabe,
title = "The OHSU biomedical question answering system framework",
abstract = "The Oregon Health & Science University submission to the TREC 2007 Genomics Track approached the entity list question answering task using a modular object oriented system framework. A system object coordinates a collection of processing objects into a pipe that constructs a set of queries, retrieves passage, and then processes those passages into a final output answer set. Using the framework we applied multiple levels of synonym expansion and a ranked series of topic queries with a range of specificities in order to retrieve all of the likely relevant passages with the most likely ranked higher. We then applied sentence pruning to the head and tail of each passage using both NLP and term-based techniques. Overall scores finished around the TREC Genomics mean for each of the four measures. Careful passage retrieval, including synonym expansion and multiple query construction, as well as sentence pruning was essential in achieving acceptable performance on this task.",
author = "Aaron Cohen and J. Yang and S. Fisher and B. Roark and Hersh, {William (Bill)}",
year = "2007",
language = "English (US)",
booktitle = "NIST Special Publication",

}

TY - GEN

T1 - The OHSU biomedical question answering system framework

AU - Cohen, Aaron

AU - Yang, J.

AU - Fisher, S.

AU - Roark, B.

AU - Hersh, William (Bill)

PY - 2007

Y1 - 2007

N2 - The Oregon Health & Science University submission to the TREC 2007 Genomics Track approached the entity list question answering task using a modular object oriented system framework. A system object coordinates a collection of processing objects into a pipe that constructs a set of queries, retrieves passage, and then processes those passages into a final output answer set. Using the framework we applied multiple levels of synonym expansion and a ranked series of topic queries with a range of specificities in order to retrieve all of the likely relevant passages with the most likely ranked higher. We then applied sentence pruning to the head and tail of each passage using both NLP and term-based techniques. Overall scores finished around the TREC Genomics mean for each of the four measures. Careful passage retrieval, including synonym expansion and multiple query construction, as well as sentence pruning was essential in achieving acceptable performance on this task.

AB - The Oregon Health & Science University submission to the TREC 2007 Genomics Track approached the entity list question answering task using a modular object oriented system framework. A system object coordinates a collection of processing objects into a pipe that constructs a set of queries, retrieves passage, and then processes those passages into a final output answer set. Using the framework we applied multiple levels of synonym expansion and a ranked series of topic queries with a range of specificities in order to retrieve all of the likely relevant passages with the most likely ranked higher. We then applied sentence pruning to the head and tail of each passage using both NLP and term-based techniques. Overall scores finished around the TREC Genomics mean for each of the four measures. Careful passage retrieval, including synonym expansion and multiple query construction, as well as sentence pruning was essential in achieving acceptable performance on this task.

UR - http://www.scopus.com/inward/record.url?scp=84873439552&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873439552&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84873439552

BT - NIST Special Publication

ER -