Cargando…

A question-entailment approach to question answering

BACKGROUND: One of the challenges in large-scale information retrieval (IR) is developing fine-grained and domain-specific methods to answer natural language questions. Despite the availability of numerous sources and datasets for answer retrieval, Question Answering (QA) remains a challenging probl...

Descripción completa

Detalles Bibliográficos
Autores principales: Ben Abacha, Asma, Demner-Fushman, Dina
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6805558/
https://www.ncbi.nlm.nih.gov/pubmed/31640539
http://dx.doi.org/10.1186/s12859-019-3119-4
_version_ 1783461413968150528
author Ben Abacha, Asma
Demner-Fushman, Dina
author_facet Ben Abacha, Asma
Demner-Fushman, Dina
author_sort Ben Abacha, Asma
collection PubMed
description BACKGROUND: One of the challenges in large-scale information retrieval (IR) is developing fine-grained and domain-specific methods to answer natural language questions. Despite the availability of numerous sources and datasets for answer retrieval, Question Answering (QA) remains a challenging problem due to the difficulty of the question understanding and answer extraction tasks. One of the promising tracks investigated in QA is mapping new questions to formerly answered questions that are “similar”. RESULTS: We propose a novel QA approach based on Recognizing Question Entailment (RQE) and we describe the QA system and resources that we built and evaluated on real medical questions. First, we compare logistic regression and deep learning methods for RQE using different kinds of datasets including textual inference, question similarity, and entailment in both the open and clinical domains. Second, we combine IR models with the best RQE method to select entailed questions and rank the retrieved answers. To study the end-to-end QA approach, we built the MedQuAD collection of 47,457 question-answer pairs from trusted medical sources which we introduce and share in the scope of this paper. Following the evaluation process used in TREC 2017 LiveQA, we find that our approach exceeds the best results of the medical task with a 29.8% increase over the best official score. CONCLUSIONS: The evaluation results support the relevance of question entailment for QA and highlight the effectiveness of combining IR and RQE for future QA efforts. Our findings also show that relying on a restricted set of reliable answer sources can bring a substantial improvement in medical QA.
format Online
Article
Text
id pubmed-6805558
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-68055582019-10-24 A question-entailment approach to question answering Ben Abacha, Asma Demner-Fushman, Dina BMC Bioinformatics Research Article BACKGROUND: One of the challenges in large-scale information retrieval (IR) is developing fine-grained and domain-specific methods to answer natural language questions. Despite the availability of numerous sources and datasets for answer retrieval, Question Answering (QA) remains a challenging problem due to the difficulty of the question understanding and answer extraction tasks. One of the promising tracks investigated in QA is mapping new questions to formerly answered questions that are “similar”. RESULTS: We propose a novel QA approach based on Recognizing Question Entailment (RQE) and we describe the QA system and resources that we built and evaluated on real medical questions. First, we compare logistic regression and deep learning methods for RQE using different kinds of datasets including textual inference, question similarity, and entailment in both the open and clinical domains. Second, we combine IR models with the best RQE method to select entailed questions and rank the retrieved answers. To study the end-to-end QA approach, we built the MedQuAD collection of 47,457 question-answer pairs from trusted medical sources which we introduce and share in the scope of this paper. Following the evaluation process used in TREC 2017 LiveQA, we find that our approach exceeds the best results of the medical task with a 29.8% increase over the best official score. CONCLUSIONS: The evaluation results support the relevance of question entailment for QA and highlight the effectiveness of combining IR and RQE for future QA efforts. Our findings also show that relying on a restricted set of reliable answer sources can bring a substantial improvement in medical QA. BioMed Central 2019-10-22 /pmc/articles/PMC6805558/ /pubmed/31640539 http://dx.doi.org/10.1186/s12859-019-3119-4 Text en © Ben Abacha and Demner-Fushman. 2019 Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.
spellingShingle Research Article
Ben Abacha, Asma
Demner-Fushman, Dina
A question-entailment approach to question answering
title A question-entailment approach to question answering
title_full A question-entailment approach to question answering
title_fullStr A question-entailment approach to question answering
title_full_unstemmed A question-entailment approach to question answering
title_short A question-entailment approach to question answering
title_sort question-entailment approach to question answering
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6805558/
https://www.ncbi.nlm.nih.gov/pubmed/31640539
http://dx.doi.org/10.1186/s12859-019-3119-4
work_keys_str_mv AT benabachaasma aquestionentailmentapproachtoquestionanswering
AT demnerfushmandina aquestionentailmentapproachtoquestionanswering
AT benabachaasma questionentailmentapproachtoquestionanswering
AT demnerfushmandina questionentailmentapproachtoquestionanswering