Zero-Shot Adaptive Transfer for Conversational Language Understanding

TL;DR

This paper presents a zero-shot transfer method for conversational slot tagging that leverages slot descriptions to enable efficient, domain-adaptive language understanding without requiring explicit concept alignments, significantly outperforming previous methods.

Contribution

Introduces a novel zero-shot transfer approach for slot tagging that uses slot descriptions, reducing training time and improving performance across multiple domains.

Findings

Outperforms previous state-of-the-art systems by a large margin.

Achieves higher accuracy especially in low data regimes.

Demonstrates effectiveness across 10 domains.

Abstract

Conversational agents such as Alexa and Google Assistant constantly need to increase their language understanding capabilities by adding new domains. A massive amount of labeled data is required for training each new domain. While domain adaptation approaches alleviate the annotation cost, prior approaches suffer from increased training time and suboptimal concept alignments. To tackle this, we introduce a novel Zero-Shot Adaptive Transfer method for slot tagging that utilizes the slot description for transferring reusable concepts across domains, and enjoys efficient training without any explicit concept alignments. Extensive experimentation over a dataset of 10 domains relevant to our commercial personal digital assistant shows that our model outperforms previous state-of-the-art systems by a large margin, and achieves an even higher improvement in the low data regime.