Fine-grained Information Status Classification Using Discourse Context-Aware Self-Attention
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 discourse context-aware self-attention neural network model for fine-grained IS classification. On the ISNotes corpus (Markert et al., 2012), our model with the contextually-encoded word representations (BERT) (Devlin et al., 2018) achieves new state-of-the-art performances on fine-grained IS classification, obtaining a 4.1% absolute overall accuracy improvement compared to Hou et al. (2013a). More importantly, we also show an improvement of 3.9% F1 for bridging anaphora recognition without using any complex hand-crafted semantic features designed for capturing the bridging phenomenon.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Fine-grained Information Status Classification Using Discourse Context-Aware BERT
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 fe…
General ClassificationIncremental Fine-grained Information Status Classification Using Attention-based LSTMs
Information status plays an important role in discourse processing. According to the hearer{'}s common sense knowledge and his comprehension of the preceding text, a discourse entity could be old, mediated or new. In thi…
ClassificationCommon Sense ReasoningGeneral ClassificationLearning the Fine-Grained Information Status of Discourse Entities
End-to-end Neural Information Status Classification
Most previous studies on information status (IS) classification and bridging anaphora recognition assume that the gold mention or syntactic tree information is given (Hou et al., 2013; Roesiger et al., 2018; Hou, 2020; Y…
Classification