A Multi-strategy Query Processing Approach for Biomedical Question Answering: USTB_PRIR at BioASQ 2017 Task 5B

Zan-Xia Jin, Bo-Wen Zhang, Fan Fang, Le-Le Zhang, Xu-Cheng Yin


Abstract
This paper describes the participation of USTB_PRIR team in the 2017 BioASQ 5B on question answering, including document retrieval, snippet retrieval, and concept retrieval task. We introduce different multimodal query processing strategies to enrich query terms and assign different weights to them. Specifically, sequential dependence model (SDM), pseudo-relevance feedback (PRF), fielded sequential dependence model (FSDM) and Divergence from Randomness model (DFRM) are respectively performed on different fields of PubMed articles, sentences extracted from relevant articles, the five terminologies or ontologies (MeSH, GO, Jochem, Uniprot and DO) to achieve better search performances. Preliminary results show that our systems outperform others in the document and snippet retrieval task in the first two batches.
Anthology ID:
W17-2348
Volume:
BioNLP 2017
Month:
August
Year:
2017
Address:
Vancouver, Canada,
Venues:
BioNLP | WS
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
373–380
Language:
URL:
https://www.aclweb.org/anthology/W17-2348
DOI:
10.18653/v1/W17-2348
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-2348.pdf