Saved in:
Bibliographic Details
Main Authors: Li, Zhijian, Larson, Stefan, Leach, Kevin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.05640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916152866766848
author Li, Zhijian
Larson, Stefan
Leach, Kevin
author_facet Li, Zhijian
Larson, Stefan
Leach, Kevin
contents Intent classifiers must be able to distinguish when a user's utterance does not belong to any supported intent to avoid producing incorrect and unrelated system responses. Although out-of-scope (OOS) detection for intent classifiers has been studied, previous work has not yet studied changes in classifier performance against hard-negative out-of-scope utterances (i.e., inputs that share common features with in-scope data, but are actually out-of-scope). We present an automated technique to generate hard-negative OOS data using ChatGPT. We use our technique to build five new hard-negative OOS datasets, and evaluate each against three benchmark intent classifiers. We show that classifiers struggle to correctly identify hard-negative OOS utterances more than general OOS utterances. Finally, we show that incorporating hard-negative OOS data for training improves model robustness when detecting hard-negative OOS data and general OOS data. Our technique, datasets, and evaluation address an important void in the field, offering a straightforward and inexpensive way to collect hard-negative OOS data and improve intent classifiers' robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2403_05640
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification
Li, Zhijian
Larson, Stefan
Leach, Kevin
Computation and Language
Intent classifiers must be able to distinguish when a user's utterance does not belong to any supported intent to avoid producing incorrect and unrelated system responses. Although out-of-scope (OOS) detection for intent classifiers has been studied, previous work has not yet studied changes in classifier performance against hard-negative out-of-scope utterances (i.e., inputs that share common features with in-scope data, but are actually out-of-scope). We present an automated technique to generate hard-negative OOS data using ChatGPT. We use our technique to build five new hard-negative OOS datasets, and evaluate each against three benchmark intent classifiers. We show that classifiers struggle to correctly identify hard-negative OOS utterances more than general OOS utterances. Finally, we show that incorporating hard-negative OOS data for training improves model robustness when detecting hard-negative OOS data and general OOS data. Our technique, datasets, and evaluation address an important void in the field, offering a straightforward and inexpensive way to collect hard-negative OOS data and improve intent classifiers' robustness.
title Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification
topic Computation and Language
url https://arxiv.org/abs/2403.05640