Skip to Main content Skip to Navigation
Conference papers

Lightweight Adapter Tuning for Multilingual Speech Translation

Abstract : Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of only a small number of taskspecific trainable parameters. While adapter tuning was investigated for multilingual neural machine translation, this paper proposes a comprehensive analysis of adapters for multilingual speech translation (ST). Starting from different pre-trained models (a multilingual ST trained on parallel data or a multilingual BART (mBART) trained on non-parallel multilingual data), we show that adapters can be used to: (a) efficiently specialize ST to specific language pairs with a low extra cost in terms of parameters, and (b) transfer from an automatic speech recognition (ASR) task and an mBART pretrained model to a multilingual ST task. Experiments show that adapter tuning offer competitive results to full fine-tuning, while being much more parameter-efficient.
Document type :
Conference papers
Complete list of metadata
Contributor : Didier Schwab <>
Submitted on : Wednesday, July 21, 2021 - 6:14:10 PM
Last modification on : Tuesday, July 27, 2021 - 3:38:40 AM


Files produced by the author(s)


  • HAL Id : hal-03294912, version 1




Hang Le, Juan Pino, Changhan Wang, Jiatao Gu, Didier Schwab, et al.. Lightweight Adapter Tuning for Multilingual Speech Translation. The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), Aug 2021, Bangkok (Virtual), Thailand. ⟨hal-03294912⟩



Record views


Files downloads