Improving Health Question Answering with Reliable and Time-Aware Evidence Retrieval

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In today's digital world, seeking answers to health questions on the Internet is a common practice. However, existing question answering (QA) systems often rely on using pre-selected and annotated evidence documents, thus making them inadequate for addressing novel questions. Our study focuses on the open-domain QA setting, where the key challenge is to first uncover relevant evidence in large knowledge bases. By utilizing the common retrieve-then-read QA pipeline and PubMed as a trustworthy collection of medical research documents, we answer health questions from three diverse datasets. We modify different retrieval settings to observe their influence on the QA pipeline's performance, including the number of retrieved documents, sentence selection process, the publication year of articles, and their number of citations. Our results reveal that cutting down on the amount of retrieved documents and favoring more recent and highly cited documents can improve the final macro F1 score up to 10%. We discuss the results, highlight interesting examples, and outline challenges for future research, like managing evidence disagreement and crafting user-friendly explanations.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationNAACL 2024 - Findings
EditorsKevin Duh, Helena Gomez, Steven Bethard
PublisherAssociation for Computational Linguistics (ACL)
Pages4752-4763
Number of pages12
ISBN (Electronic)9798891761193
DOIs
StatePublished - 2024
Event2024 Findings of the Association for Computational Linguistics: NAACL 2024 - Mexico City, Mexico
Duration: 16 Jun 202421 Jun 2024

Publication series

NameFindings of the Association for Computational Linguistics: NAACL 2024 - Findings

Conference

Conference2024 Findings of the Association for Computational Linguistics: NAACL 2024
Country/TerritoryMexico
CityMexico City
Period16/06/2421/06/24

Fingerprint

Dive into the research topics of 'Improving Health Question Answering with Reliable and Time-Aware Evidence Retrieval'. Together they form a unique fingerprint.

Cite this