Abstract
In this work, we propose a novel segmental hypergraph representation to model overlapping entity mentions that are prevalent in many practical datasets. We show that our model built on top of such a new representation is able to capture features and interactions that cannot be captured by previous models while maintaining a low time complexity for inference. We also present a theoretical analysis to formally assess how our representation is better than alternative representations reported in the literature in terms of representational power. Coupled with neural networks for feature learning, our model achieves the state-of-the-art performance in three benchmark datasets annotated with overlapping mentions.- Anthology ID:
- D18-1019
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 204–214
- Language:
- URL:
- https://aclanthology.org/D18-1019
- DOI:
- 10.18653/v1/D18-1019
- Cite (ACL):
- Bailin Wang and Wei Lu. 2018. Neural Segmental Hypergraphs for Overlapping Mention Recognition. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 204–214, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Neural Segmental Hypergraphs for Overlapping Mention Recognition (Wang & Lu, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D18-1019.pdf
- Data
- ACE 2004, ACE 2005, CoNLL-2003, GENIA, NNE