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

By Varun Kumar, Hadrien Glaude, Cyprien de Lichy, W. Campbell. 2019

91 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Survey of Data Augmentation Approaches for NLP (2021, methodology): “Kumar et al. (2019a) train seq2seq models with their proposed method DiPS which learns to generate diverse paraphrases of input text using a modiﬁed decoder with a submodular objective, and show its effectiveness as DA for several classi-ﬁcation tasks.”
Neural Data Augmentation via Example Extrapolation (2021, methodology): “Our approach has strong connections to several recent works on using language models for data augmentation (Kumar et al., 2019) and zero-shot learning (Brown et al.”
Data Augmentation using Pre-trained Transformer Models (2020, background): “Further, the proposed data augmentation techniques can also be combined with latent space augmentation (Kumar et al., 2019).”
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems (2020, background): “…dialogue systems have been explored to improve DST (Song et al., 2020; Yoo et al., 2020; Cam-pagna et al., 2020), Natural Language Understanding (NLU) (Peng et al., 2020c), intent classiﬁcation (Kumar et al., 2019) and hybrid end-to-end systems (Zhang et al., 2019a; Rastogi et al., 2019).”
Named Entity Recognition for Social Media Texts with Semantic Augmentation (2020, background): “Inspired by studies using semantic augmentation (especially from lexical semantics) to improve model performance on many NLP tasks (Song and Xia, 2013; Song et al., 2018a; Kumar et al., 2019; Amjad et al., 2020), it is also a potential promising solution to solving social media NER.”