Coreferential Reasoning Learning for Language Representation

Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However, most existing language representation models cannot explicitly handle coreference, which is essential to the coherent understanding of the whole discourse. To address this issue, we present CorefBERT, a novel language representation model that can capture the coreferential relations in context. The experimental results show that, compared with existing baseline models, CorefBERT can achieve significant improvements consistently on various downstream NLP tasks that require coreferential reasoning, while maintaining comparable performance to previous models on other common NLP tasks. The source code and experiment details of this paper can be obtained from

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction DocRED CorefRoBERTa-large F1 60.25 # 31
Ign F1 57.90 # 32
Relation Extraction DocRED CorefBERT-base F1 56.96 # 46
Ign F1 54.54 # 46
Relation Extraction DocRED CorefBERT-large F1 58.83 # 40
Ign F1 56.40 # 41