SpanBERT: Improving Pre-training by Representing and Predicting Spans

07/24/2019

∙

by   Mandar Joshi, et al.

∙

Princeton University

∙

Facebook

∙

University of Washington

∙

0

∙

share

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random tokens, and (2) training the span boundary representations to predict the entire content of the masked span, without relying on the individual token representations within it. SpanBERT consistently outperforms BERT and our better-tuned baselines, with substantial gains on span selection tasks such as question answering and coreference resolution. In particular, with the same training data and model size as BERT-large, our single model obtains 94.6 respectively. We also achieve a new state of the art on the OntoNotes coreference resolution task (79.6 benchmark (70.8