Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature
Abstract
Information overload is a prevalent challenge in many high-value domains. A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months. In general, biomedical literature expands by two papers every minute, totalling over a million new papers every year. Search in the biomedical realm, and many other vertical domains is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. We propose a general approach for vertical search based on domain-specific pretraining and present a case study for the biomedical domain. Despite being substantially simpler and not using any relevance labels for training or development, our method performs comparably or better than the best systems in the official TREC-COVID evaluation, a COVID-related biomedical search competition. Using distributed computing in modern cloud infrastructure, our system can scale to tens of millions of articles on PubMed and has been deployed as Microsoft Biomedical Search, a new search experience for biomedical literature: https://aka.ms/biomedsearch.
Cite
@article{arxiv.2106.13375,
title = {Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature},
author = {Yu Wang and Jinchao Li and Tristan Naumann and Chenyan Xiong and Hao Cheng and Robert Tinn and Cliff Wong and Naoto Usuyama and Richard Rogahn and Zhihong Shen and Yang Qin and Eric Horvitz and Paul N. Bennett and Jianfeng Gao and Hoifung Poon},
journal= {arXiv preprint arXiv:2106.13375},
year = {2021}
}
Comments
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2021 Applied Data Science Track