A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification

Varun Kumar, Hadrien Glaude, Cyprien de Lichy, Wlliam Campbell


Abstract
New conversation topics and functionalities are constantly being added to conversational AI agents like Amazon Alexa and Apple Siri. As data collection and annotation is not scalable and is often costly, only a handful of examples for the new functionalities are available, which results in poor generalization performance. We formulate it as a Few-Shot Integration (FSI) problem where a few examples are used to introduce a new intent. In this paper, we study six feature space data augmentation methods to improve classification performance in FSI setting in combination with both supervised and unsupervised representation learning methods such as BERT. Through realistic experiments on two public conversational datasets, SNIPS, and the Facebook Dialog corpus, we show that data augmentation in feature space provides an effective way to improve intent classification performance in few-shot setting beyond traditional transfer learning approaches. In particular, we show that (a) upsampling in latent space is a competitive baseline for feature space augmentation (b) adding the difference between two examples to a new example is a simple yet effective data augmentation method.
Anthology ID:
D19-6101
Volume:
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Colin Cherry, Greg Durrett, George Foster, Reza Haffari, Shahram Khadivi, Nanyun Peng, Xiang Ren, Swabha Swayamdipta
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–10
Language:
URL:
https://aclanthology.org/D19-6101
DOI:
10.18653/v1/D19-6101
Bibkey:
Cite (ACL):
Varun Kumar, Hadrien Glaude, Cyprien de Lichy, and Wlliam Campbell. 2019. A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 1–10, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification (Kumar et al., 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-6101.pdf
Attachment:
 D19-6101.Attachment.zip
Data
SNIPS