Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages

arXiv:2404.02588v1 Announce Type: new
Abstract: Spoken Language Understanding (SLU) models are a core component of voice assistants (VA), such as Alexa, Bixby, and Google Assistant. In this paper, we introduce a pipeline designed to extend SLU systems to new languages, utilizing Large Language Models (LLMs) that we fine-tune for machine translation of slot-annotated SLU training data. Our approach improved on the MultiATIS++ benchmark, a primary multi-language SLU dataset, in the cloud scenario using an mBERT model. Specifically, we saw an …

abstract alexa arxiv assistant assistants bixby core cs.cl expansion google google assistant language language models languages language understanding large language large language models llms paper pipeline slu spoken spoken language understanding systems type understanding voice voice assistants