Towards a Unified Multi-Domain Multilingual Named Entity Recognition Model
Mayank Kulkarni, Daniel Preotiuc-Pietro, Karthik Radhakrishnan, Genta Indra Winata, Shijie Wu, Lingjue Xie, Shaohua Yang
Abstract
Named Entity Recognition is a key Natural Language Processing task whose performance is sensitive to choice of genre and language. A unified NER model across multiple genres and languages is more practical and efficient by leveraging commonalities across genres or languages. In this paper, we propose a novel setup for NER which includes multi-domain and multilingual training and evaluation across 13 domains and 4 languages. We explore a range of approaches to building a unified model using domain and language adaptation techniques. Our experiments highlight multiple nuances to consider while building a unified model, including that naive data pooling fails to obtain good performance, that domain-specific adaptations are more important than language-specific ones and that including domain-specific adaptations in a unified model nears the performance of training multiple dedicated monolingual models at a fraction of their parameter count.- Anthology ID:
- 2023.eacl-main.161
- 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:
- 2210–2219
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.161
- DOI:
- 10.18653/v1/2023.eacl-main.161
- Cite (ACL):
- Mayank Kulkarni, Daniel Preotiuc-Pietro, Karthik Radhakrishnan, Genta Indra Winata, Shijie Wu, Lingjue Xie, and Shaohua Yang. 2023. Towards a Unified Multi-Domain Multilingual Named Entity Recognition Model. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2210–2219, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Towards a Unified Multi-Domain Multilingual Named Entity Recognition Model (Kulkarni et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.eacl-main.161.pdf