To What Degree Can Language Borders Be Blurred In BERT-based Multilingual Spoken Language Understanding?
This work addresses the problem of improving cross-lingual transfer in spoken language understanding for multilingual AI systems, representing an incremental advancement.
The paper investigates how well BERT-based multilingual spoken language understanding models transfer knowledge across languages, finding substantial performance even on distant languages but a gap to ideal multilingual performance, and proposes a novel adversarial model that narrows this gap.
This paper addresses the question as to what degree a BERT-based multilingual Spoken Language Understanding (SLU) model can transfer knowledge across languages. Through experiments we will show that, although it works substantially well even on distant language groups, there is still a gap to the ideal multilingual performance. In addition, we propose a novel BERT-based adversarial model architecture to learn language-shared and language-specific representations for multilingual SLU. Our experimental results prove that the proposed model is capable of narrowing the gap to the ideal multilingual performance.