Exploring Description-Augmented Dataless Intent Classification

Anonymous

TL;DR: We introduce methods to create intent label descriptions for dataless classification (IC) and compare against strong 0-shot baselines on 3 IC datasets to show dataless methods can surpass zero-shot in certain cases without training on labelled data

Abstract: In this work, we introduce several schemes to leverage description-augmented embedding similarity for dataless intent classification using current state-of-the-art (SOTA) text embedding models. We report results of our methods on three commonly used intent classification datasets and compare against previous works of a similar nature. Our work shows promising results for dataless classification scaling to a large number of unseen intents, yielding competitive results to, and in some situations outperforming strong zero-shot baselines, all without training on labelled or task-specific data. Furthermore, we provide qualitative error analysis of the shortfalls of this methodology to help guide future research in this area.

Paper Type: long

Research Area: Efficient/Low-Resource Methods for NLP

Contribution Types: NLP engineering experiment, Approaches to low-resource settings

Languages Studied: English