SpanBERT: Improving Pre-training by Representing and Predicting Spans
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 conte...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
The MIT Press
2020-07-01
|
Series: | Transactions of the Association for Computational Linguistics |
Online Access: | https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00300 |