Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering
This work addresses coreference resolution for natural language processing applications, representing an incremental improvement over existing end-to-end neural models.
The paper tackled coreference resolution by proposing a neural model that uses biaffine attention for antecedent scoring and joint optimization of mention detection and clustering, achieving state-of-the-art performance on the CoNLL-2012 English test set.
Coreference resolution aims to identify in a text all mentions that refer to the same real-world entity. The state-of-the-art end-to-end neural coreference model considers all text spans in a document as potential mentions and learns to link an antecedent for each possible mention. In this paper, we propose to improve the end-to-end coreference resolution system by (1) using a biaffine attention model to get antecedent scores for each possible mention, and (2) jointly optimizing the mention detection accuracy and the mention clustering log-likelihood given the mention cluster labels. Our model achieves the state-of-the-art performance on the CoNLL-2012 Shared Task English test set.