@inproceedings{li-etal-2021-multilingual,
title = "Multilingual Speech Translation from Efficient Finetuning of Pretrained Models",
author = "Li, Xian and
Wang, Changhan and
Tang, Yun and
Tran, Chau and
Tang, Yuqing and
Pino, Juan and
Baevski, Alexei and
Conneau, Alexis and
Auli, Michael",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.68",
doi = "10.18653/v1/2021.acl-long.68",
pages = "827--838",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2021-multilingual">
<titleInfo>
<title>Multilingual Speech Translation from Efficient Finetuning of Pretrained Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changhan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chau</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqing</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexei</namePart>
<namePart type="family">Baevski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Conneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Auli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">li-etal-2021-multilingual</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.68</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.68</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>827</start>
<end>838</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Speech Translation from Efficient Finetuning of Pretrained Models
%A Li, Xian
%A Wang, Changhan
%A Tang, Yun
%A Tran, Chau
%A Tang, Yuqing
%A Pino, Juan
%A Baevski, Alexei
%A Conneau, Alexis
%A Auli, Michael
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F li-etal-2021-multilingual
%X 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.
%R 10.18653/v1/2021.acl-long.68
%U https://aclanthology.org/2021.acl-long.68
%U https://doi.org/10.18653/v1/2021.acl-long.68
%P 827-838
Markdown (Informal)
[Multilingual Speech Translation from Efficient Finetuning of Pretrained Models](https://aclanthology.org/2021.acl-long.68) (Li et al., ACL-IJCNLP 2021)
ACL
- Xian Li, Changhan Wang, Yun Tang, Chau Tran, Yuqing Tang, Juan Pino, Alexei Baevski, Alexis Conneau, and Michael Auli. 2021. Multilingual Speech Translation from Efficient Finetuning of Pretrained Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 827–838, Online. Association for Computational Linguistics.