Composed Variational Natural Language Generation for Few-shot Intents

Congying Xia, Caiming Xiong, Philip Yu, Richard Socher


Abstract
In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario. To build connections between existing many-shot intents and few-shot intents, we consider an intent as a combination of a domain and an action, and propose a composed variational natural language generator (CLANG), a transformer-based conditional variational autoencoder. CLANG utilizes two latent variables to represent the utterances corresponding to two different independent parts (domain and action) in the intent, and the latent variables are composed together to generate natural examples. Additionally, to improve the generator learning, we adopt the contrastive regularization loss that contrasts the in-class with the out-of-class utterance generation given the intent. To evaluate the quality of the generated utterances, experiments are conducted on the generalized few-shot intent detection task. Empirical results show that our proposed model achieves state-of-the-art performances on two real-world intent detection datasets.
Anthology ID:
2020.findings-emnlp.303
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:
3379–3388
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.303
DOI:
10.18653/v1/2020.findings-emnlp.303
Bibkey:
Cite (ACL):
Congying Xia, Caiming Xiong, Philip Yu, and Richard Socher. 2020. Composed Variational Natural Language Generation for Few-shot Intents. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3379–3388, Online. Association for Computational Linguistics.
Cite (Informal):
Composed Variational Natural Language Generation for Few-shot Intents (Xia et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.303.pdf
Video:
 https://slideslive.com/38940699