To refer to this page use:
|Abstract:||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 BERTlarge, our single model obtains 94.6% and 88.7% F1 on SQuAD 1.1 and 2.0 respectively. We also achieve a new state of the art on the OntoNotes coreference resolution task (79.6% F1), strong performance on the TACRED relation extraction benchmark, and even gains on GLUE.|
|Citation:||Joshi, Mandar, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. "SpanBERT: Improving Pre-training by Representing and Predicting Spans." Transactions of the Association for Computational Linguistics 8 (2020): 64-77. doi:10.1162/tacl_a_00300|
|Pages:||64 - 77|
|Type of Material:||Journal Article|
|Journal/Proceeding Title:||Transactions of the Association for Computational Linguistics|
|Version:||Final published version. This is an open access article.|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.