Coreferential Reasoning Learning for Language Representation
Authors:
Preprint
Abstract
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 https://github.com/thunlp/CorefBERT.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- SpanBERT: Improving Pre-training by Representing and Predicting SpansTransactions of the Association for Computational Linguistics, 2020
- HIN: Hierarchical Inference Network for Document-Level Relation Extraction2020
- A Simple and Effective Model for Answering Multi-span Questions2020
- Neural Network Acceptability JudgmentsTransactions of the Association for Computational Linguistics, 2019
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- VideoBERT: A Joint Model for Video and Language Representation Learning2019
- Knowledge Enhanced Contextual Word Representations2019
- Mind the GAP: A Balanced Corpus of Gendered Ambiguous PronounsTransactions of the Association for Computational Linguistics, 2018
- The First Winograd Schema Challenge at IJCAI‐16AI Magazine, 2017
- Long Short-Term MemoryNeural Computation, 1997