Cross-lingual Multi-task Transfer for Zero-shot Task-oriented Dialog

Digital assistants are becoming an integral part of everyday life. However, commercial digital assistants are only available for a limited set of languages. Because of this, a vast amount of people can not use these devices in their native tongue.
In this work, we focus on two core tasks within the digital assistant pipeline: intent classification and slot detection. Intent classification recovers the goal of the utterance, whereas slot detection identifies important properties regarding this goal. Besides introducing a novel cross-lingual dataset for these tasks, consisting of 11 languages, we evaluate a variety of models: 1)
multilingually pretrained transformer-based models, 2) we supplement these models with auxiliary tasks to evaluate whether multi-task learning can be beneficial, and 3) annotation transfer with neural machine translation.