Coreference Aware Representation Learning for Neural Named Entity Recognition

Coreference Aware Representation Learning for Neural Named Entity Recognition

Zeyu Dai, Hongliang Fei, Ping Li

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 4946-4953. https://doi.org/10.24963/ijcai.2019/687

Recent neural network models have achieved state-of-the-art performance on the task of named entity recognition (NER). However, previous neural network models typically treat the input sentences as a linear sequence of words but ignore rich structural information, such as the coreference relations among non-adjacent words, phrases or entities. In this paper, we propose a novel approach to learn coreference-aware word representations for the NER task at the document level. In particular, we enrich the well-known neural architecture ``CNN-BiLSTM-CRF'' with a coreference layer on top of the BiLSTM layer to incorporate coreferential relations. Furthermore, we introduce the coreference regularization to ensure the coreferential entities to share similar representations and consistent predictions within the same coreference cluster. Our proposed model achieves new state-of-the-art performance on two NER benchmarks: CoNLL-2003 and OntoNotes v5.0. More importantly, we demonstrate that our framework does not rely on gold coreference knowledge, and can still work well even when the coreferential relations are generated by a third-party toolkit.
Keywords:
Natural Language Processing: Information Extraction
Natural Language Processing: Natural Language Processing
Natural Language Processing: Tagging, chunking, and parsing
Natural Language Processing: Named Entities