A Question-Entailment Approach to Question Answering

Abstract

One of the challenges in large-scale information retrieval (IR) is to develop 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 to map new questions to formerly answered questions that are `similar'. In this paper, 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 machine learning 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, that 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. The evaluation results also 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.

References in corpus (4)

• Neural Natural Language Inference Models Enhanced with External Knowledge
• Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
• CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
• CMU LiveMedQA at TREC 2017 LiveQA: A Consumer Health Question Answering System

Cited by in corpus (18)

• Biomedical Question Answering: A Survey of Approaches and Challenges
• A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine
• Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems
• Automated Question Answer medical model based on Deep Learning Technology
• Medical Question Summarization with Entity-driven Contrastive Learning
• Learning Contextualized Document Representations for Healthcare Answer Retrieval
• Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition
• Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond
• BIOMRC: A Dataset for Biomedical Machine Reading Comprehension
• LLM-based IR-system for Bank Supervisors
• Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to COVID-19 FAQs
• Self-supervised Answer Retrieval on Clinical Notes
• Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation
• Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset
• Pentagon at MEDIQA 2019: Multi-task Learning for Filtering and Re-ranking Answers using Language Inference and Question Entailment
• GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation
• A Grounded Well-being Conversational Agent with Multiple Interaction Modes: Preliminary Results
• COVIDRead: A Large-scale Question Answering Dataset on COVID-19