Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Park, Gyutae, Baek, Ingeol, Kim, ByeongJeong, Shin, Joongbo, Lee, Hwanhee
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909435951054848
author Park, Gyutae
Baek, Ingeol
Kim, ByeongJeong
Shin, Joongbo
Lee, Hwanhee
author_facet Park, Gyutae
Baek, Ingeol
Kim, ByeongJeong
Shin, Joongbo
Lee, Hwanhee
contents Dialogue intent classification aims to identify the underlying purpose or intent of a user's input in a conversation. Current intent classification systems encounter considerable challenges, primarily due to the vast number of possible intents and the significant semantic overlap among similar intent classes. In this paper, we propose a novel approach to few-shot dialogue intent classification through in-context learning, incorporating dynamic label refinement to address these challenges. Our method retrieves relevant examples for a test input from the training set and leverages a large language model to dynamically refine intent labels based on semantic understanding, ensuring that intents are clearly distinguishable from one another. Experimental results demonstrate that our approach effectively resolves confusion between semantically similar intents, resulting in significantly enhanced performance across multiple datasets compared to baselines. We also show that our method generates more interpretable intent labels, and has a better semantic coherence in capturing underlying user intents compared to baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15603
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification
Park, Gyutae
Baek, Ingeol
Kim, ByeongJeong
Shin, Joongbo
Lee, Hwanhee
Computation and Language
Dialogue intent classification aims to identify the underlying purpose or intent of a user's input in a conversation. Current intent classification systems encounter considerable challenges, primarily due to the vast number of possible intents and the significant semantic overlap among similar intent classes. In this paper, we propose a novel approach to few-shot dialogue intent classification through in-context learning, incorporating dynamic label refinement to address these challenges. Our method retrieves relevant examples for a test input from the training set and leverages a large language model to dynamically refine intent labels based on semantic understanding, ensuring that intents are clearly distinguishable from one another. Experimental results demonstrate that our approach effectively resolves confusion between semantically similar intents, resulting in significantly enhanced performance across multiple datasets compared to baselines. We also show that our method generates more interpretable intent labels, and has a better semantic coherence in capturing underlying user intents compared to baselines.
title Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification
topic Computation and Language
url https://arxiv.org/abs/2412.15603