AFD-SLU: Adaptive Feature Distillation for Spoken Language Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Yan, Cui, Yibo, Xie, Liang, Yin, Erwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908827134197760
author Xie, Yan
Cui, Yibo
Xie, Liang
Yin, Erwei
author_facet Xie, Yan
Cui, Yibo
Xie, Liang
Yin, Erwei
contents Spoken Language Understanding (SLU) is a core component of conversational systems, enabling machines to interpret user utterances. Despite its importance, developing effective SLU systems remains challenging due to the scarcity of labeled training data and the computational burden of deploying Large Language Models (LLMs) in real-world applications. To further alleviate these issues, we propose an Adaptive Feature Distillation framework that transfers rich semantic representations from a General Text Embeddings (GTE)-based teacher model to a lightweight student model. Our method introduces a dynamic adapter equipped with a Residual Projection Neural Network (RPNN) to align heterogeneous feature spaces, and a Dynamic Distillation Coefficient (DDC) that adaptively modulates the distillation strength based on real-time feedback from intent and slot prediction performance. Experiments on the Chinese profile-based ProSLU benchmark demonstrate that AFD-SLU achieves state-of-the-art results, with 95.67% intent accuracy, 92.02% slot F1 score, and 85.50% overall accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04821
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AFD-SLU: Adaptive Feature Distillation for Spoken Language Understanding
Xie, Yan
Cui, Yibo
Xie, Liang
Yin, Erwei
Computation and Language
Spoken Language Understanding (SLU) is a core component of conversational systems, enabling machines to interpret user utterances. Despite its importance, developing effective SLU systems remains challenging due to the scarcity of labeled training data and the computational burden of deploying Large Language Models (LLMs) in real-world applications. To further alleviate these issues, we propose an Adaptive Feature Distillation framework that transfers rich semantic representations from a General Text Embeddings (GTE)-based teacher model to a lightweight student model. Our method introduces a dynamic adapter equipped with a Residual Projection Neural Network (RPNN) to align heterogeneous feature spaces, and a Dynamic Distillation Coefficient (DDC) that adaptively modulates the distillation strength based on real-time feedback from intent and slot prediction performance. Experiments on the Chinese profile-based ProSLU benchmark demonstrate that AFD-SLU achieves state-of-the-art results, with 95.67% intent accuracy, 92.02% slot F1 score, and 85.50% overall accuracy.
title AFD-SLU: Adaptive Feature Distillation for Spoken Language Understanding
topic Computation and Language
url https://arxiv.org/abs/2509.04821