Abstract
We study three general multi-task learning (MTL) approaches on 11 sequence tagging tasks. Our extensive empirical results show that in about 50% of the cases, jointly learning all 11 tasks improves upon either independent or pairwise learning of the tasks. We also show that pairwise MTL can inform us what tasks can benefit others or what tasks can be benefited if they are learned jointly. In particular, we identify tasks that can always benefit others as well as tasks that can always be harmed by others. Interestingly, one of our MTL approaches yields embeddings of the tasks that reveal the natural clustering of semantic and syntactic tasks. Our inquiries have opened the doors to further utilization of MTL in NLP.- Anthology ID:
- C18-1251
- Volume:
- Proceedings of the 27th International Conference on Computational Linguistics
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico, USA
- Editors:
- Emily M. Bender, Leon Derczynski, Pierre Isabelle
- Venue:
- COLING
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2965–2977
- Language:
- URL:
- https://aclanthology.org/C18-1251
- DOI:
- Cite (ACL):
- Soravit Changpinyo, Hexiang Hu, and Fei Sha. 2018. Multi-Task Learning for Sequence Tagging: An Empirical Study. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2965–2977, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Task Learning for Sequence Tagging: An Empirical Study (Changpinyo et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/C18-1251.pdf
- Data
- CoNLL 2003, English Web Treebank, FrameNet, STREUSLE, Universal Dependencies