# Locale-agnostic Universal Domain Classification Model in Spoken Language Understanding

## TL;DR

This paper presents a locale-agnostic universal domain classification model for spoken language understanding that leverages multi-task learning to improve accuracy across multiple locales with limited data, reducing scaling costs.

## Contribution

It introduces a novel selective multi-task learning approach for joint representation learning across locales with different domain sets, enhancing classification performance.

## Key findings

- Outperforms baseline models in multi-locale domain classification
- Effective in classifying locale-specific and low-resource domains
- Reduces data requirements for new locales

## Abstract

In this paper, we introduce an approach for leveraging available data across multiple locales sharing the same language to 1) improve domain classification model accuracy in Spoken Language Understanding and user experience even if new locales do not have sufficient data and 2) reduce the cost of scaling the domain classifier to a large number of locales. We propose a locale-agnostic universal domain classification model based on selective multi-task learning that learns a joint representation of an utterance over locales with different sets of domains and allows locales to share knowledge selectively depending on the domains. The experimental results demonstrate the effectiveness of our approach on domain classification task in the scenario of multiple locales with imbalanced data and disparate domain sets. The proposed approach outperforms other baselines models especially when classifying locale-specific domains and also low-resourced domains.