On the cross-lingual transferability of multilingual prototypical models across NLU tasks
This work addresses the challenge of under-resourced languages in task-oriented dialog, though it is incremental as it builds on existing transfer learning and meta-learning methods.
The paper tackles the problem of cross-lingual transfer in natural language understanding for low-resource languages by combining few-shot learning with prototypical neural networks and multilingual Transformers, resulting in substantial performance improvements on the MultiATIS++ corpus.
Supervised deep learning-based approaches have been applied to task-oriented dialog and have proven to be effective for limited domain and language applications when a sufficient number of training examples are available. In practice, these approaches suffer from the drawbacks of domain-driven design and under-resourced languages. Domain and language models are supposed to grow and change as the problem space evolves. On one hand, research on transfer learning has demonstrated the cross-lingual ability of multilingual Transformers-based models to learn semantically rich representations. On the other, in addition to the above approaches, meta-learning have enabled the development of task and language learning algorithms capable of far generalization. Through this context, this article proposes to investigate the cross-lingual transferability of using synergistically few-shot learning with prototypical neural networks and multilingual Transformers-based models. Experiments in natural language understanding tasks on MultiATIS++ corpus shows that our approach substantially improves the observed transfer learning performances between the low and the high resource languages. More generally our approach confirms that the meaningful latent space learned in a given language can be can be generalized to unseen and under-resourced ones using meta-learning.