Exploring Logically Dependent Multi-task Learning with Causal Inference

Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, Yaohui Jin


Abstract
Previous studies have shown that hierarchical multi-task learning (MTL) can utilize task dependencies by stacking encoders and outperform democratic MTL. However, stacking encoders only considers the dependencies of feature representations and ignores the label dependencies in logically dependent tasks. Furthermore, how to properly utilize the labels remains an issue due to the cascading errors between tasks. In this paper, we view logically dependent MTL from the perspective of causal inference and suggest a mediation assumption instead of the confounding assumption in conventional MTL models. We propose a model including two key mechanisms: label transfer (LT) for each task to utilize the labels of all its lower-level tasks, and Gumbel sampling (GS) to deal with cascading errors. In the field of causal inference, GS in our model is essentially a counterfactual reasoning process, trying to estimate the causal effect between tasks and utilize it to improve MTL. We conduct experiments on two English datasets and one Chinese dataset. Experiment results show that our model achieves state-of-the-art on six out of seven subtasks and improves predictions’ consistency.
Anthology ID:
2020.emnlp-main.173
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2213–2225
Language:
URL:
https://aclanthology.org/2020.emnlp-main.173
DOI:
10.18653/v1/2020.emnlp-main.173
Bibkey:
Cite (ACL):
Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, and Yaohui Jin. 2020. Exploring Logically Dependent Multi-task Learning with Causal Inference. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2213–2225, Online. Association for Computational Linguistics.
Cite (Informal):
Exploring Logically Dependent Multi-task Learning with Causal Inference (Chen et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.173.pdf
Video:
 https://slideslive.com/38938694