Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables

TL;DR

This paper introduces a zero-shot cross-lingual dialogue system that leverages minimal parallel data and latent variables to improve natural language understanding in low-resource languages, outperforming existing models.

Contribution

It presents a novel approach combining cross-lingual word alignment and latent variable modeling for zero-shot multilingual dialogue understanding.

Findings

Achieves better intent detection and slot filling in low-resource languages.

Uses fewer external resources than previous models.

Outperforms state-of-the-art zero-shot cross-lingual models.

Abstract

Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios. Hence, we propose a zero-shot adaptation of task-oriented dialogue system to low-resource languages. To tackle this challenge, we first use a set of very few parallel word pairs to refine the aligned cross-lingual word-level representations. We then employ a latent variable model to cope with the variance of similar sentences across different languages, which is induced by imperfect cross-lingual alignments and inherent differences in languages. Finally, the experimental results show that even though we utilize much less external resources, our model achieves better adaptation performance for natural language understanding task (i.e., the intent detection and slot filling) compared to the current state-of-the-art model in the zero-shot scenario.