Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.02588 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911826130763776 |
|---|---|
| author | Hoscilowicz, Jakub Pawlowski, Pawel Skorupa, Marcin Sowański, Marcin Janicki, Artur |
| author_facet | Hoscilowicz, Jakub Pawlowski, Pawel Skorupa, Marcin Sowański, Marcin Janicki, Artur |
| contents | 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 improvement in the Overall Accuracy metric: from 53% to 62.18%, compared to the existing state-of-the-art method, Fine and Coarse-grained Multi-Task Learning Framework (FC-MTLF). In the on-device scenario (tiny and not pretrained SLU), our method improved the Overall Accuracy from 5.31% to 22.06% over the baseline Global-Local Contrastive Learning Framework (GL-CLeF) method. Contrary to both FC-MTLF and GL-CLeF, our LLM-based machine translation does not require changes in the production architecture of SLU. Additionally, our pipeline is slot-type independent: it does not require any slot definitions or examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02588 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages Hoscilowicz, Jakub Pawlowski, Pawel Skorupa, Marcin Sowański, Marcin Janicki, Artur Computation and Language 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 improvement in the Overall Accuracy metric: from 53% to 62.18%, compared to the existing state-of-the-art method, Fine and Coarse-grained Multi-Task Learning Framework (FC-MTLF). In the on-device scenario (tiny and not pretrained SLU), our method improved the Overall Accuracy from 5.31% to 22.06% over the baseline Global-Local Contrastive Learning Framework (GL-CLeF) method. Contrary to both FC-MTLF and GL-CLeF, our LLM-based machine translation does not require changes in the production architecture of SLU. Additionally, our pipeline is slot-type independent: it does not require any slot definitions or examples. |
| title | Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.02588 |