Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language Understanding
This work addresses multilingual spoken language understanding with slot filling, offering incremental improvements in performance across several datasets.
The authors tackled the problem of End-to-End Spoken Language Understanding (E2E-SLU) in multilingual settings with lexical filler prediction, proposing a unified method that integrates pretrained speech and text models. They achieved state-of-the-art results on two datasets and improved the best known result on the PortMEDIA-Language dataset by almost half, reaching a Concept/Value Error Rate of 23.65%.
A number of methods have been proposed for End-to-End Spoken Language Understanding (E2E-SLU) using pretrained models, however their evaluation often lacks multilingual setup and tasks that require prediction of lexical fillers, such as slot filling. In this work, we propose a unified method that integrates multilingual pretrained speech and text models and performs E2E-SLU on six datasets in four languages in a generative manner, including the prediction of lexical fillers. We investigate how the proposed method can be improved by pretraining on widely available speech recognition data using several training objectives. Pretraining on 7000 hours of multilingual data allows us to outperform the state-of-the-art ultimately on two SLU datasets and partly on two more SLU datasets. Finally, we examine the cross-lingual capabilities of the proposed model and improve on the best known result on the PortMEDIA-Language dataset by almost half, achieving a Concept/Value Error Rate of 23.65%.