Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection

Hoang Nguyen, Chenwei Zhang, Congying Xia, Philip Yu


Abstract
Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Although recent works demonstrate that multi-level matching plays an important role in transferring learned knowledge from seen training classes to novel testing classes, they rely on a static similarity measure and overly fine-grained matching components. These limitations inhibit generalizing capability towards Generalized Few-shot Learning settings where both seen and novel classes are co-existent. In this paper, we propose a novel Semantic Matching and Aggregation Network where semantic components are distilled from utterances via multi-head self-attention with additional dynamic regularization constraints. These semantic components capture high-level information, resulting in more effective matching between instances. Our multi-perspective matching method provides a comprehensive matching measure to enhance representations of both labeled and unlabeled instances. We also propose a more challenging evaluation setting that considers classification on the joint all-class label space. Extensive experimental results demonstrate the effectiveness of our method. Our code and data are publicly available.
Anthology ID:
2020.findings-emnlp.108
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1209–1218
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.108
DOI:
10.18653/v1/2020.findings-emnlp.108
Bibkey:
Cite (ACL):
Hoang Nguyen, Chenwei Zhang, Congying Xia, and Philip Yu. 2020. Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1209–1218, Online. Association for Computational Linguistics.
Cite (Informal):
Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection (Nguyen et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.108.pdf
Optional supplementary material:
 2020.findings-emnlp.108.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38940168
Code
 nhhoang96/Semantic_Matching