Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Krückl, Xaver Maria, Blaschke, Verena, Plank, Barbara
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910775853973504
author Krückl, Xaver Maria
Blaschke, Verena
Plank, Barbara
author_facet Krückl, Xaver Maria
Blaschke, Verena
Plank, Barbara
contents Reliable slot and intent detection (SID) is crucial in natural language understanding for applications like digital assistants. Encoder-only transformer models fine-tuned on high-resource languages generally perform well on SID. However, they struggle with dialectal data, where no standardized form exists and training data is scarce and costly to produce. We explore zero-shot transfer learning for SID, focusing on multiple Bavarian dialects, for which we release a new dataset for the Munich dialect. We evaluate models trained on auxiliary tasks in Bavarian, and compare joint multi-task learning with intermediate-task training. We also compare three types of auxiliary tasks: token-level syntactic tasks, named entity recognition (NER), and language modelling. We find that the included auxiliary tasks have a more positive effect on slot filling than intent classification (with NER having the most positive effect), and that intermediate-task training yields more consistent performance gains. Our best-performing approach improves intent classification performance on Bavarian dialects by 5.1 and slot filling F1 by 8.4 percentage points.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03863
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study
Krückl, Xaver Maria
Blaschke, Verena
Plank, Barbara
Computation and Language
Reliable slot and intent detection (SID) is crucial in natural language understanding for applications like digital assistants. Encoder-only transformer models fine-tuned on high-resource languages generally perform well on SID. However, they struggle with dialectal data, where no standardized form exists and training data is scarce and costly to produce. We explore zero-shot transfer learning for SID, focusing on multiple Bavarian dialects, for which we release a new dataset for the Munich dialect. We evaluate models trained on auxiliary tasks in Bavarian, and compare joint multi-task learning with intermediate-task training. We also compare three types of auxiliary tasks: token-level syntactic tasks, named entity recognition (NER), and language modelling. We find that the included auxiliary tasks have a more positive effect on slot filling than intent classification (with NER having the most positive effect), and that intermediate-task training yields more consistent performance gains. Our best-performing approach improves intent classification performance on Bavarian dialects by 5.1 and slot filling F1 by 8.4 percentage points.
title Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study
topic Computation and Language
url https://arxiv.org/abs/2501.03863