Zero-Shot Slot and Intent Detection in Low-Resource Languages

TL;DR

This paper explores zero-shot intent detection and slot filling in low-resource languages using large language models, demonstrating significant performance improvements over baselines.

Contribution

It introduces the application of the mT0 model for zero-shot SID tasks in low-resource languages, showing its strong generalization capabilities.

Findings

Best model outperforms baseline by up to +30 F1 points

Large language models can generalize well to unseen languages in SID tasks

Multitask prompting enhances zero-shot performance in low-resource settings

Abstract

Intent detection and slot filling are critical tasks in spoken and natural language understanding for task-oriented dialog systems. In this work we describe our participation in the slot and intent detection for low-resource language varieties (SID4LR; Aepli et al. (2023)). We investigate the slot and intent detection (SID) tasks using a wide range of models and settings. Given the recent success of multitask-prompted finetuning of large language models, we also test the generalization capability of the recent encoder-decoder model mT0 (Muennighoff et al., 2022) on new tasks (i.e., SID) in languages they have never intentionally seen. We show that our best model outperforms the baseline by a large margin (up to +30 F1 points) in both SID tasks