Abstract
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.- Anthology ID:
- 2020.coling-main.243
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 2699–2709
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.243
- DOI:
- 10.18653/v1/2020.coling-main.243
- Cite (ACL):
- Quynh Do, Judith Gaspers, Tobias Roeding, and Melanie Bradford. 2020. To What Degree Can Language Borders Be Blurred In BERT-based Multilingual Spoken Language Understanding?. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2699–2709, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- To What Degree Can Language Borders Be Blurred In BERT-based Multilingual Spoken Language Understanding? (Do et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2020.coling-main.243.pdf