Multi-domain Spoken Language Understanding Using Domain- And Task-aware Parameterization

Abstract

Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain. However, annotating data for each domain is both financially costly and non-scalable so we should fully utilize information across all domains. One existing approach solves the problem by conducting multi-domain learning, using shared parameters for joint training across domains. We propose to improve the parameterization of this method by using domain-specific and task-specific model parameters to improve knowledge learning and transfer. Experiments on 5 domains show that our model is more effective for multi-domain SLU and obtain the best results. In addition, we show its transferability by outperforming the prior best model by 12.4% when adapting to a new domain with little data.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyqin2020multi

Related papers

• Style Attuned Pre-training And Parameter Efficient Fine-tuning For Spoken Language Understanding (2020)6.77
• Multi-domain Adversarial Learning For Slot Filling In Spoken Language Understanding (2017)0.00
• Locale-agnostic Universal Domain Classification Model In Spoken Language Understanding (2019)5.24
• Unislu: Unified Spoken Language Understanding From Heterogeneous Cross-task Datasets (2025)0.00
• A Dual Task Learning Approach To Fine-tune A Multilingual Semantic Speech Encoder For Spoken Language Understanding (2024)0.00
• Unsupervised Transfer Learning For Spoken Language Understanding In Intelligent Agents (2018)0.00
• Curriculum-based Transfer Learning For An Effective End-to-end Spoken Language Understanding And Domain Portability (2019)10.74
• Large-scale Transfer Learning For Low-resource Spoken Language Understanding (2020)2.26