Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network

Yutai Hou, Wanxiang Che, Yongkui Lai, Zhihan Zhou, Yijia Liu, Han Liu, Ting Liu


Abstract
In this paper, we explore the slot tagging with only a few labeled support sentences (a.k.a. few-shot). Few-shot slot tagging faces a unique challenge compared to the other fewshot classification problems as it calls for modeling the dependencies between labels. But it is hard to apply previously learned label dependencies to an unseen domain, due to the discrepancy of label sets. To tackle this, we introduce a collapsed dependency transfer mechanism into the conditional random field (CRF) to transfer abstract label dependency patterns as transition scores. In the few-shot setting, the emission score of CRF can be calculated as a word’s similarity to the representation of each label. To calculate such similarity, we propose a Label-enhanced Task-Adaptive Projection Network (L-TapNet) based on the state-of-the-art few-shot classification model – TapNet, by leveraging label name semantics in representing labels. Experimental results show that our model significantly outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.
Anthology ID:
2020.acl-main.128
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:
1381–1393
Language:
URL:
https://aclanthology.org/2020.acl-main.128
DOI:
10.18653/v1/2020.acl-main.128
Bibkey:
Cite (ACL):
Yutai Hou, Wanxiang Che, Yongkui Lai, Zhihan Zhou, Yijia Liu, Han Liu, and Ting Liu. 2020. Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1381–1393, Online. Association for Computational Linguistics.
Cite (Informal):
Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network (Hou et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.128.pdf
Video:
 http://slideslive.com/38929212
Code
 AtmaHou/FewShotTagging +  additional community code
Data
GUM