CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering
Authors:
- XinliangXIXinliang
- Simon LinSLSimon Lin
Preprint
Abstract
Clinical question answering (QA) aims to automatically answer questions from medical professionals based on clinical texts. Studies show that neural QA models trained on one corpus may not generalize well to new clinical texts from a different institute or a different patient group, where large-scale QA pairs are not readily available for retraining. To address this challenge, we propose a simple yet effective framework, CliniQG4QA, which leverages question generation (QG) to synthesize QA pairs on new clinical contexts and boosts QA models without requiring manual annotations. In order to generate diverse types of questions that are essential for training QA models, we further introduce a seq2seq-based question phrase prediction (QPP) module that can be used together with most existing QG models to diversify their generation. Our comprehensive experiment results show that the QA corpus generated by our framework is helpful to improve QA models on the new contexts (up to 8% absolute gain in terms of Exact Match), and that the QPP module plays a crucial role in achieving the gain.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus2020
- On the Generation of Medical Question-Answer PairsProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Unsupervised Domain Adaptation on Reading ComprehensionProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Adapting and evaluating a deep learning language model for clinical why-question answeringJAMIA Open, 2020
- Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset2020
- An ontology for clinical questions about the contents of patient notesJournal of Biomedical Informatics, 2012
- Classifier chains for multi-label classificationMachine Learning, 2011
- A theory of learning from different domainsMachine Learning, 2009
- The Meteor metric for automatic evaluation of machine translationMachine Translation, 2009
- Learning multi-label scene classificationPattern Recognition, 2004