Abstract
Previous work on bridging anaphora recognition (Hou et al., 2013) 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 performances on fine-grained IS classification, obtaining a 4.8 absolute overall accuracy improvement compared to Hou et al. (2013). 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.- Anthology ID:
- 2020.coling-main.537
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 6101–6112
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.537
- DOI:
- 10.18653/v1/2020.coling-main.537
- Cite (ACL):
- Yufang Hou. 2020. Fine-grained Information Status Classification Using Discourse Context-Aware BERT. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6101–6112, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- Fine-grained Information Status Classification Using Discourse Context-Aware BERT (Hou, COLING 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.coling-main.537.pdf
- Code
- IBM/bridging-resolution