Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study
This work addresses the challenge of natural language understanding for digital assistants in low-resource dialectal settings, representing an incremental advance with domain-specific impact.
The paper tackled the problem of slot and intent detection in dialectal data, specifically Bavarian dialects, by exploring zero-shot transfer learning with auxiliary tasks, resulting in improvements of 5.1 percentage points for intent classification and 8.4 F1 points for slot filling.
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.