Instance-Guided Prompt Learning for Few-Shot Text Matching

Jia Du, Xuanyu Zhang, Siyi Wang, Kai Wang, Yanquan Zhou, Lei Li, Qing Yang, Dongliang Xu


Abstract
Few-shot text matching is a more practical technique in natural language processing (NLP) to determine whether two texts are semantically identical. They primarily design patterns to reformulate text matching into a pre-trained task with uniform prompts across all instances. But they fail to take into account the connection between prompts and instances. This paper argues that dynamically strengthening the correlation between particular instances and the prompts is necessary because fixed prompts cannot adequately fit all diverse instances in inference. We suggest IGATE: Instance-Guided prompt leArning for few-shoT tExt matching, a novel pluggable prompt learning method. The gate mechanism used by IGATE, which is between the embedding and the PLM encoders, makes use of the semantics of instances to regulate the effects of the gate on the prompt tokens. The experimental findings show that IGATE achieves SOTA performance on MRPC and QQP, outperforming strong baselines. GitHub will host the release of codes.
Anthology ID:
2022.findings-emnlp.285
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3880–3886
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.285
DOI:
10.18653/v1/2022.findings-emnlp.285
Bibkey:
Cite (ACL):
Jia Du, Xuanyu Zhang, Siyi Wang, Kai Wang, Yanquan Zhou, Lei Li, Qing Yang, and Dongliang Xu. 2022. Instance-Guided Prompt Learning for Few-Shot Text Matching. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3880–3886, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Instance-Guided Prompt Learning for Few-Shot Text Matching (Du et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.285.pdf