CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization

Abstract

The COVID-19 global pandemic has resulted in international efforts to understand, track, and mitigate the disease, yielding a significant corpus of COVID-19 and SARS-CoV-2-related publications across scientific disciplines. As of May 2020, 128,000 coronavirus-related publications have been collected through the COVID-19 Open Research Dataset Challenge. Here we present CO-Search, a retriever-ranker semantic search engine designed to handle complex queries over the COVID-19 literature, potentially aiding overburdened health workers in finding scientific answers during a time of crisis. The retriever is built from a Siamese-BERT encoder that is linearly composed with a TF-IDF vectorizer, and reciprocal-rank fused with a BM25 vectorizer. The ranker is composed of a multi-hop question-answering module, that together with a multi-paragraph abstractive summarizer adjust retriever scores. To account for the domain-specific and relatively limited dataset, we generate a bipartite graph of document paragraphs and citations, creating 1.3 million (citation title, paragraph) tuples for training the encoder. We evaluate our system on the data of the TREC-COVID information retrieval challenge. CO-Search obtains top performance on the datasets of the first and second rounds, across several key metrics: normalized discounted cumulative gain, precision, mean average precision, and binary preference.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Unified Language Model Pre-training for Natural Language Understanding and Generation
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• CORD-19: The COVID-19 Open Research Dataset
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Rapidly Bootstrapping a Question Answering Dataset for COVID-19
• Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset: Preliminary Thoughts and Lessons Learned
• TREC-COVID: Constructing a Pandemic Information Retrieval Test Collection
• Controllable Abstractive Summarization

Cited by in corpus (7)

• Pre-trained Language Models in Biomedical Domain: A Systematic Survey
• Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations
• Extracting Summary Knowledge Graphs from Long Documents
• Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
• Interpretable Self-supervised Multi-task Learning for COVID-19 Information Retrieval and Extraction
• A Self-supervised Approach for Semantic Indexing in the Context of COVID-19 Pandemic
• COVIDRead: A Large-scale Question Answering Dataset on COVID-19