The University of Texas at Dallas HLTRI's Participation in EPIC-QA: Searching for Entailed Questions Revealing Novel Answer Nuggets
This work addresses the problem of improving question answering accuracy for COVID-19 information, targeting both expert and consumer users, and is incremental as it builds on existing IR and entailment methods.
The paper tackled answering COVID-19 questions by developing a multi-phase neural IR system that uses entailment relations between questions to re-rank answers based on novel nuggets, achieving promising results with excellence in the Expert QA task.
The Epidemic Question Answering (EPIC-QA) track at the Text Analysis Conference (TAC) is an evaluation of methodologies for answering ad-hoc questions about the COVID-19 disease. This paper describes our participation in both tasks of EPIC-QA, targeting: (1) Expert QA and (2) Consumer QA. Our methods used a multi-phase neural Information Retrieval (IR) system based on combining BM25, BERT, and T5 as well as the idea of considering entailment relations between the original question and questions automatically generated from answer candidate sentences. Moreover, because entailment relations were also considered between all generated questions, we were able to re-rank the answer sentences based on the number of novel answer nuggets they contained, as indicated by the processing of a question entailment graph. Our system, called SEaRching for Entailed QUestions revealing NOVel nuggets of Answers (SER4EQUNOVA), produced promising results in both EPIC-QA tasks, excelling in the Expert QA task.