A question-entailment approach to question answering

By Asma Ben Abacha, Dina Demner-Fushman. BMC Bioinformatics, 2019

305 citations recorded by the source corpus.

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”. 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. 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.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/86c8e5e2979377f87c7fdb2108497d074943d462

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Benchmarking Retrieval-Augmented Generation for Medicine (2024, background): “…AG is reasonably comprehensive, there are other potentially useful resources that can also be incorporated into M ED R AG in future work, such as the full-text articles from PubMed Central (PMC) 7 and Frequently Asked Questions (FAQs) from trustworthy sources (Ben Abacha and Demner-Fushman, 2019).”
Combining Similarity and Transformer Methods for Case Law Entailment (2019, background): “For example, question-answering systems may apply textual entailment techniques to identify an answer from previously stored databases [3], [24].”
What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams (2020, methodology): “Among them, LiveQA [24], Medication QA [25], MEDIQA [26], and MedQuAD [27] contain consumer health related questions and the answers are obtained by searching healthcare websites such as MedlinePlus via the ChiQA system [28] and selecting a snippet of searching results out, where the answer retrieva”
COVIDRead: A Large-scale Question Answering Dataset on COVID-19 (2021, background): “One of the studies like [25] has showed the potential of Question Entailment in improvement of QA system.”
Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks (2021, unknown): “Using entailment models to enhance the performance of QA tasks has been extensively studied (Harabagiu and Hickl, 2006; Sacaleanu et al., 2008; Abacha and Demner-Fushman, 2019; Trivedi et al., 2019).”
BioMRC: A Dataset for Biomedical Machine Reading Comprehension (2020, methodology): “Several biomedical MRC datasets exist, but have orders of magnitude fewer questions than BIOMRC (Ben Abacha and Demner-Fushman, 2019) or are not suitable for a cloze-style MRC task (Pampari et al., 2018; Ben Abacha et al., 2019; Zhang et al., 2018).”
Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to COVID-19 FAQs (2020, result): “The closest to our work is that of Abacha and Demner-Fushman [3, 4].”
The TellTail of Embeddings: Fingerprinting Retrievers in Black-Box Systems (2026, unknown): “We further validate our findings on MedicalQARetrieval [40], [53], [54], a small, semantically dense dataset comprising approximately 2.4K passages focused on medical topics (the results, consistent with MS MARCO’s, are in App.”
Towards Domain Specification of Embedding Models in Medicine (2025, unknown): “Finally, the MedQuAD corpus supplies 47457 question–answer pairs sourced from authoritative outlets such as the National Cancer Institute, enriching the benchmark with diverse consumer-health inquiries [39].”