Fine-grained Information Status Classification Using Discourse Context-Aware BERT
This work addresses natural language processing tasks for computational linguistics, offering incremental improvements over prior methods.
The paper tackled fine-grained information status classification and bridging anaphora recognition by proposing a discourse context-aware BERT model, achieving a 4.8% accuracy improvement and a 10.5 F1 point gain without hand-crafted features.
Previous work on bridging anaphora recognition (Hou et al., 2013a) casts the problem as a subtask of learning fine-grained information status (IS). However, these systems heavily depend on many hand-crafted linguistic features. In this paper, we propose a simple discourse context-aware BERT model for fine-grained IS classification. On the ISNotes corpus (Markert et al., 2012), our model achieves new state-of-the-art performance on fine-grained IS classification, obtaining a 4.8 absolute overall accuracy improvement compared to Hou et al. (2013a). More importantly, we also show an improvement of 10.5 F1 points for bridging anaphora recognition without using any complex hand-crafted semantic features designed for capturing the bridging phenomenon. We further analyze the trained model and find that the most attended signals for each IS category correspond well to linguistic notions of information status.