Abstract
Cross-domain NER is a challenging yet practical problem. Entity mentions can be highly different across domains. However, the correlations between entity types can be relatively more stable across domains. We investigate a multi-cell compositional LSTM structure for multi-task learning, modeling each entity type using a separate cell state. With the help of entity typed units, cross-domain knowledge transfer can be made in an entity type level. Theoretically, the resulting distinct feature distributions for each entity type make it more powerful for cross-domain transfer. Empirically, experiments on four few-shot and zero-shot datasets show our method significantly outperforms a series of multi-task learning methods and achieves the best results.- Anthology ID:
- 2020.acl-main.524
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5906–5917
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.524
- DOI:
- 10.18653/v1/2020.acl-main.524
- Cite (ACL):
- Chen Jia and Yue Zhang. 2020. Multi-Cell Compositional LSTM for NER Domain Adaptation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5906–5917, Online. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Cell Compositional LSTM for NER Domain Adaptation (Jia & Zhang, ACL 2020)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2020.acl-main.524.pdf