Multi-Task Learning of Pairwise Sequence Classification Tasks over Disparate Label Spaces

Isabelle Augenstein, Sebastian Ruder, Anders Søgaard


Abstract
We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of tasks with disparate label spaces. We outperform strong single and multi-task baselines and achieve a new state of the art for aspect-based and topic-based sentiment analysis.
Anthology ID:
N18-1172
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1896–1906
Language:
URL:
https://aclanthology.org/N18-1172
DOI:
10.18653/v1/N18-1172
Bibkey:
Cite (ACL):
Isabelle Augenstein, Sebastian Ruder, and Anders Søgaard. 2018. Multi-Task Learning of Pairwise Sequence Classification Tasks over Disparate Label Spaces. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1896–1906, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Multi-Task Learning of Pairwise Sequence Classification Tasks over Disparate Label Spaces (Augenstein et al., NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-1172.pdf
Video:
 https://aclanthology.org/N18-1172.mp4
Code
 coastalcph/mtl-disparate