SpanBERT: Improving Pre-training by Representing and Predicting Spans
Citations Over TimeTop 1% of 2020 papers
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 BERT large , 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. 1
Related Papers
- → (2019)31,533 cited
- → HISTORIAE, History of Socio-Cultural Transformation as Linguistic Data Science. A Humanities Use Case(2019)17,204 cited
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding(2018)