On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning

Tingting Ma, Qianhui Wu, Zhiwei Yu, Tiejun Zhao, Chin-Yew Lin


Abstract
Recent studies on few-shot intent detection have attempted to formulate the task as a meta-learning problem, where a meta-learning model is trained with a certain capability to quickly adapt to newly specified few-shot tasks with potentially unseen intent categories. Prototypical networks have been commonly used in this setting, with the hope that good prototypical representations could be learned to capture the semantic similarity between the query and a few labeled instances. This intuition naturally leaves a question of whether or not a good sentence representation scheme could suffice for the task without further domain-specific adaptation. In this paper, we conduct empirical studies on a number of general-purpose sentence embedding schemes, showing that good sentence embeddings without any fine-tuning on intent detection data could produce a non-trivially strong performance. Inspired by the results from our qualitative analysis, we propose a frustratingly easy modification, which leads to consistent improvements over all sentence encoding schemes, including those from the state-of-the-art prototypical network variants with task-specific fine-tuning.
Anthology ID:
2022.naacl-main.279
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3806–3818
Language:
URL:
https://aclanthology.org/2022.naacl-main.279
DOI:
10.18653/v1/2022.naacl-main.279
Bibkey:
Cite (ACL):
Tingting Ma, Qianhui Wu, Zhiwei Yu, Tiejun Zhao, and Chin-Yew Lin. 2022. On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3806–3818, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning (Ma et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.279.pdf
Code
 microsoft/KC
Data
MultiNLISNLI