paper-with-me

Papers

Fine-grained Information Status Classification Using Discourse Context-Aware Self-Attention

2019-08-13 · Yufang Hou

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.

📄 PDF Abstract BibTeX arXiv:1908.04755

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

Fine-grained Information Status Classification Using Discourse Context-Aware BERT

2020-10-26 · COLING 2020 8 · Yufang Hou

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 Classification

Incremental Fine-grained Information Status Classification Using Attention-based LSTMs

2016-12-01 · COLING 2016 12 · Yufang Hou

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 Classification

Learning the Fine-Grained Information Status of Discourse Entities

2012-04-01 · EACL 2012 4 · Altaf Rahman, Vincent Ng
Bridging Anaphora Resolution

End-to-end Neural Information Status Classification

2021-09-06 · Findings (EMNLP) 2021 11 · Yufang Hou

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

Collective Classification for Fine-grained Information Status

2012-07-01 · ACL 2012 7 · Katja Markert, Yufang Hou, Michael Strube
ClassificationCoreference ResolutionGeneral Classification