Exploring Description-Augmented Dataless Intent Classification

Ruoyu Hu, Foaad Khosmood, Abbas Edalat
7/25/2024
cs.CL

No official code found. Best implementation: ruoyunlp/dataless-intent-classification (0 stars, last commit 2025-09-22).

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 four 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. We show competitive results and significant improvements (+6.12\% Avg.) over 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.

View on arXivView PDF

Code Implementations(1)

ruoyunlp/dataless-intent-classificationCommunity100%
00Shell, PythonJul 1, 20241 years ago

Similar Papers

Generate then Refine: Data Augmentation for Zero-shot Intent Detection

83% match1 repo62024

How DDAIR you? Disambiguated Data Augmentation for Intent Recognition

80% match1 repo2026

Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework

78% match1 repo62025

Generalized zero-shot audio-to-intent classification

78% match2023

REIC: RAG-Enhanced Intent Classification at Scale

78% match2025

Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification

78% match1 repo52024

Cite this paper

@article{hu2024exploring,
  title  = {Exploring Description-Augmented Dataless Intent Classification},
  author = {Ruoyu Hu and Foaad Khosmood and Abbas Edalat},
  year   = {2024},
  eprint = {2407.17862},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.17862v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.17862.svg)](https://codeofpaper.com/paper/2407.17862)

Discussion