CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management

Abstract

We present CAiRE-COVID, a real-time question answering (QA) and multi-document summarization system, which won one of the 10 tasks in the Kaggle COVID-19 Open Research Dataset Challenge, judged by medical experts. Our system aims to tackle the recent challenge of mining the numerous scientific articles being published on COVID-19 by answering high priority questions from the community and summarizing salient question-related information. It combines information extraction with state-of-the-art QA and query-focused multi-document summarization techniques, selecting and highlighting evidence snippets from existing literature given a query. We also propose query-focused abstractive and extractive multi-document summarization methods, to provide more relevant information related to the question. We further conduct quantitative experiments that show consistent improvements on various metrics for each module. We have launched our website CAiRE-COVID for broader use by the medical community, and have open-sourced the code for our system, to bootstrap further study by other researches.

Accepted EMNLP2020 NLP-COVID Workshop

References in corpus (11)

• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Teaching Machines to Read and Comprehend
• CORD-19: The COVID-19 Open Research Dataset
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Leveraging BERT for Extractive Text Summarization on Lectures
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
• Rapidly Bootstrapping a Question Answering Dataset for COVID-19
• Multi-hop Reading Comprehension through Question Decomposition and Rescoring
• Query Focused Multi-Document Summarization with Distant Supervision

Cited by in corpus (5)

• Pre-trained Language Models in Biomedical Domain: A Systematic Survey
• AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization
• Model Generalization on COVID-19 Fake News Detection
• Ontology-based and User-focused Automatic Text Summarization (OATS): Using COVID-19 Risk Factors as an Example
• Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance