ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection

TL;DR

This paper investigates using ChatGPT-generated synthetic data to improve compositional generalization in open intent detection, demonstrating significant performance gains over existing methods through comprehensive benchmark evaluations.

Contribution

It introduces a novel data augmentation approach using ChatGPT to enhance compositional generalization in open intent detection tasks, addressing limitations of current benchmarks.

Findings

ChatGPT-generated data improves intent detection accuracy

Enhanced performance over existing techniques on multiple benchmarks

Synthetic data effectively captures compositional language variations

Abstract

Open intent detection, a crucial aspect of natural language understanding, involves the identification of previously unseen intents in user-generated text. Despite the progress made in this field, challenges persist in handling new combinations of language components, which is essential for compositional generalization. In this paper, we present a case study exploring the use of ChatGPT as a data augmentation technique to enhance compositional generalization in open intent detection tasks. We begin by discussing the limitations of existing benchmarks in evaluating this problem, highlighting the need for constructing datasets for addressing compositional generalization in open intent detection tasks. By incorporating synthetic data generated by ChatGPT into the training process, we demonstrate that our approach can effectively improve model performance. Rigorous evaluation of multiple benchmarks reveals that our method outperforms existing techniques and significantly enhances open intent detection capabilities. Our findings underscore the potential of large language models like ChatGPT for data augmentation in natural language understanding tasks.