XL-NBT: A Cross-lingual Neural Belief Tracking Framework
This addresses the need for cost-effective cross-lingual customer support by reducing reliance on expensive human annotations, though it is incremental as it builds on existing transfer learning methods.
The paper tackles the problem of building cross-lingual task-oriented dialog systems without annotated data in target languages by proposing a framework that uses a pre-trained teacher tracker in a source language to transfer knowledge via distillation, achieving promising results in Italian and German.
Task-oriented dialog systems are becoming pervasive, and many companies heavily rely on them to complement human agents for customer service in call centers. With globalization, the need for providing cross-lingual customer support becomes more urgent than ever. However, cross-lingual support poses great challenges---it requires a large amount of additional annotated data from native speakers. In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework. Specifically, we assume that there exists a source language with dialog belief tracking annotations while the target languages have no annotated dialog data of any form. Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data. We then distill and transfer its own knowledge to the student state tracker in target languages. We specifically discuss two types of common parallel resources: bilingual corpus and bilingual dictionary, and design different transfer learning strategies accordingly. Experimentally, we successfully use English state tracker as the teacher to transfer its knowledge to both Italian and German trackers and achieve promising results.