Zero-Shot Adaptive Transfer for Conversational Language Understanding
This work addresses the challenge of efficiently expanding conversational agents like Alexa and Google Assistant to new domains with reduced training time and annotation needs, representing an incremental improvement over prior domain adaptation approaches.
The paper tackles the problem of high annotation costs and suboptimal concept alignments in domain adaptation for conversational language understanding by introducing a Zero-Shot Adaptive Transfer method for slot tagging that uses slot descriptions to transfer concepts across domains without explicit alignments. It shows that this model outperforms previous state-of-the-art systems by a large margin on a dataset of 10 domains, with even higher improvements in low-data scenarios.
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.