Abstract
The information bottleneck (IB) principle has been proven effective in various NLP applications. The existing work, however, only used either generative or information compression models to improve the performance of the target task. In this paper, we propose to combine the two types of IB models into one system to enhance Named Entity Recognition (NER).For one type of IB model, we incorporate two unsupervised generative components, span reconstruction and synonym generation, into a span-based NER system. The span reconstruction ensures that the contextualised span representation keeps the span information, while the synonym generation makes synonyms have similar representations even in different contexts. For the other type of IB model, we add a supervised IB layer that performs information compression into the system to preserve useful features for NER in the resulting span representations. Experiments on five different corpora indicate that jointly training both generative and information compression models can enhance the performance of the baseline span-based NER system. Our source code is publicly available at https://github.com/nguyennth/joint-ib-models.- Anthology ID:
- 2023.eacl-main.146
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1984–1996
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.146
- DOI:
- 10.18653/v1/2023.eacl-main.146
- Cite (ACL):
- Nhung T. H. Nguyen, Makoto Miwa, and Sophia Ananiadou. 2023. Span-based Named Entity Recognition by Generating and Compressing Information. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1984–1996, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Span-based Named Entity Recognition by Generating and Compressing Information (Nguyen et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/revert-3132-ingestion-checklist/2023.eacl-main.146.pdf