KnowMAN: Weakly Supervised Multinomial Adversarial Networks

Luisa März, Ehsaneddin Asgari, Fabienne Braune, Franziska Zimmermann, Benjamin Roth


Abstract
The absence of labeled data for training neural models is often addressed by leveraging knowledge about the specific task, resulting in heuristic but noisy labels. The knowledge is captured in labeling functions, which detect certain regularities or patterns in the training samples and annotate corresponding labels for training. This process of weakly supervised training may result in an over-reliance on the signals captured by the labeling functions and hinder models to exploit other signals or to generalize well. We propose KnowMAN, an adversarial scheme that enables to control influence of signals associated with specific labeling functions. KnowMAN forces the network to learn representations that are invariant to those signals and to pick up other signals that are more generally associated with an output label. KnowMAN strongly improves results compared to direct weakly supervised learning with a pre-trained transformer language model and a feature-based baseline.
Anthology ID:
2021.emnlp-main.751
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9549–9557
Language:
URL:
https://aclanthology.org/2021.emnlp-main.751
DOI:
10.18653/v1/2021.emnlp-main.751
Bibkey:
Cite (ACL):
Luisa März, Ehsaneddin Asgari, Fabienne Braune, Franziska Zimmermann, and Benjamin Roth. 2021. KnowMAN: Weakly Supervised Multinomial Adversarial Networks. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9549–9557, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
KnowMAN: Weakly Supervised Multinomial Adversarial Networks (März et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.751.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.751.mp4
Code
 luisamaerz/knowman