paper-with-me

Papers

Multilingual Speech Translation from Efficient Finetuning of Pretrained Models

2021-08-01 · ACL 2021 5 · Xian Li, Changhan Wang, Yun Tang, Chau Tran, Yuqing Tang, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation through efficient transfer learning from a pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA (LayerNorm and Attention) finetuning can achieve zero-shot crosslingual and cross-modality transfer ability by only finetuning 10 50{\%} of the pretrained parameters. This effectively leverages large pretrained models at low training cost such as wav2vec 2.0 for acoustic modeling, and mBART for multilingual text generation. This sets a new state-of-the-art for 36 translation directions (and surpassing cascaded ST for 26 of them) on the large-scale multilingual ST benchmark CoVoST 2 (+6.4 BLEU on average for En-X directions and +6.7 BLEU for X-En directions). Our approach demonstrates strong zero-shot performance in a many-to-many multilingual model (+5.6 BLEU on average across 28 non-English directions), making it an appealing approach for attaining high-quality speech translation with improved parameter and data efficiency.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderSpeech-to-TextText GenerationTransfer LearningTranslation

Methods 이 논문이 사용한 방법론

mBART 설명 없음

Similar Papers 제목 키워드 기반

Multilingual Speech Translation with Efficient Finetuning of Pretrained Models

2020-10-24 · Xian Li, Changhan Wang, Yun Tang, Chau Tran 외

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA …

Cross-Lingual TransferDecoderSpeech-to-TextText Generation+2

Multilingual Translation with Extensible Multilingual Pretraining and Finetuning

2020-08-02 · Yuqing Tang, Chau Tran, Xi-An Li, Peng-Jen Chen 외

Recent work demonstrates the potential of multilingual pretraining of creating one model that can be used for various tasks in different languages. Previous work in multilingual pretraining has demonstrated that machine …

Machine TranslationTranslation

Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions

2023-05-24 · Jiahuan Li, Hao Zhou, ShuJian Huang, Shanbo Cheng 외

Large-scale Pretrained Language Models (LLMs), such as ChatGPT and GPT4, have shown strong abilities in multilingual translations, without being explicitly trained on parallel corpora. It is interesting how the LLMs obta…

Language ModelingLanguage ModellingTranslation

Amazon Alexa AI’s System for IWSLT 2022 Offline Speech Translation Shared Task

2022-05-01 · IWSLT (ACL) 2022 5 · Akshaya Shanbhogue, Ran Xue, Ching-Yun Chang, Sarah Campbell

This paper describes Amazon Alexa AI’s submission to the IWSLT 2022 Offline Speech Translation Task. Our system is an end-to-end speech translation model that leverages pretrained models and cross modality transfer learn…

Domain AdaptationTransfer LearningTranslation

Towards Multilingual Automatic Dialogue Evaluation

2023-08-31 · John Mendonça, Alon Lavie, Isabel Trancoso

The main limiting factor in the development of robust multilingual dialogue evaluation metrics is the lack of multilingual data and the limited availability of open sourced multilingual dialogue systems. In this work, we…

Dialogue EvaluationMachine TranslationTranslation