Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision

  title={Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision},
  author={Khalil Mrini and Harpreet Singh and Franck Dernoncourt and Seunghyun Yoon and Trung Bui and Walter Chang and Emilia Farcas and Ndapa Nakashole},
  booktitle={International Conference on Computational Linguistics},
Current medical question answering systems have difficulty processing long, detailed and informally worded questions submitted by patients, called Consumer Health Questions (CHQs). To address this issue, we introduce a medical question understanding and answering system with knowledge grounding and semantic self-supervision. Our system is a pipeline that first summarizes a long, medical, user-written question, using a supervised summarization loss. Then, our system performs a two-step retrieval… 

Figures and Tables from this paper



A question-entailment approach to question answering

A novel QA approach based on Recognizing Question Entailment (RQE), which exceeds the best results of the medical task with a 29.8% increase over the best official score, and highlights the effectiveness of combining IR and RQE for future QA efforts.

Medical question answering: translating medical questions into sparql queries

This paper presents a complete question analysis approach including medical entity recognition, semantic relation extraction and automatic translation to SPARQL queries, which supports the fact that SParQL can represent a wide range of natural language questions in a question-answering perspective.

Overview of the MEDIQA 2019 Shared Task on Textual Inference, Question Entailment and Question Answering

The shared task is motivated by a need to develop relevant methods, techniques and gold standards for inference and entailment in the medical domain, and their application to improve domain specific information retrieval and question answering systems.

Recognizing Question Entailment for Medical Question Answering

A new approach for the detection of similar questions based on Recognizing Question Entailment (RQE) is proposed, which considers Frequently Asked Question (FAQs) as a valuable and widespread source of information and proposes an existing answer if FAQ similar to a consumer health question exists.

Exploiting Sentence Embedding for Medical Question Answering

A supervised learning framework to exploit sentence embedding for the medical question answering task using contextual self-attention and multi-scale techniques to encode a sentence into an embedding tensor is presented.

Expanding Query Answers on Medical Knowledge Bases

A domain-specific query relaxation approach that leverages rich medical domain vocabularies and their semantic relationships from external knowledge sources, such as taxonomies, ontologies, and semantic networks, to expand the vocabulary of KBs is proposed.

On the Generation of Medical Question-Answer Pairs

An automated medical QA pair generation framework is proposed, consisting of an unsupervised key phrase detector that explores unstructured material for validity, and a generator that involves a multi-pass decoder to integrate structural knowledge for diversity.

Overview of the Medical Question Answering Task at TREC 2017 LiveQA

The task addresses the automatic answering of consumer health questions received by the U.S. National Library of Medicine, and several deep learning approaches were tested, including attentional encoder-decoder networks, long short-term memory networks and convolutional neural networks.

BioAMA: Towards an End to End BioMedical Question Answering System

A novel Biomedical Question Answering system, BioAMA: “Biomedical Ask Me Anything” on task 5b of the annual BioASQ challenge, and a novel NLI-based framework to answer the yes/no questions.