Abstract
This paper presents a novel method for nested named entity recognition. As a layered method, our method extends the prior second-best path recognition method by explicitly excluding the influence of the best path. Our method maintains a set of hidden states at each time step and selectively leverages them to build a different potential function for recognition at each level. In addition, we demonstrate that recognizing innermost entities first results in better performance than the conventional outermost entities first scheme. We provide extensive experimental results on ACE2004, ACE2005, and GENIA datasets to show the effectiveness and efficiency of our proposed method.- Anthology ID:
- 2021.acl-long.275
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3547–3557
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.275
- DOI:
- 10.18653/v1/2021.acl-long.275
- Cite (ACL):
- Yiran Wang, Hiroyuki Shindo, Yuji Matsumoto, and Taro Watanabe. 2021. Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3547–3557, Online. Association for Computational Linguistics.
- Cite (Informal):
- Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path (Wang et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2021.acl-long.275.pdf
- Code
- speedcell4/nersted
- Data
- ACE 2004, ACE 2005, GENIA