@inproceedings{zhang-etal-2022-fcgcl,
title = "{FCGCL}: Fine- and Coarse-Granularity Contrastive Learning for Speech Translation",
author = "Zhang, Hao and
Si, Nianwen and
Chen, Yaqi and
Li, Zhen and
Niu, Tong and
Yang, Xukui and
Qu, Dan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.222",
doi = "10.18653/v1/2022.findings-emnlp.222",
pages = "3048--3059",
abstract = "It is notoriously difficult to implement end-to-end speech translation (E2E-ST) model because of the task complexity and data scarcity. Existing techniques often attempt to carry out implicit knowledge transfer from machine translation (MT) to ST model by imposing various constraints. However, in this transfer scenario, a significant problem is that the performance of the MT will drop significantly and the final transfer effect is also restricted. In this article, we recommend Fine and Coarse Granularity Contrastive Learning (FCGCL), which conduct explicit knowledge transfer from MT to ST model. Specially, we ensure through multi granularity contrastive learning that inputs with similar semantic between different modalities are encoded closely in the shared semantic space while inputs with different semantics are kept apart. Experiments on the MuST-C datasets on all 8 languages and further analysis show that our method can effectively improve the E2E-ST performance and achieves an average BLEU of 29.0.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-fcgcl">
<titleInfo>
<title>FCGCL: Fine- and Coarse-Granularity Contrastive Learning for Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xukui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It is notoriously difficult to implement end-to-end speech translation (E2E-ST) model because of the task complexity and data scarcity. Existing techniques often attempt to carry out implicit knowledge transfer from machine translation (MT) to ST model by imposing various constraints. However, in this transfer scenario, a significant problem is that the performance of the MT will drop significantly and the final transfer effect is also restricted. In this article, we recommend Fine and Coarse Granularity Contrastive Learning (FCGCL), which conduct explicit knowledge transfer from MT to ST model. Specially, we ensure through multi granularity contrastive learning that inputs with similar semantic between different modalities are encoded closely in the shared semantic space while inputs with different semantics are kept apart. Experiments on the MuST-C datasets on all 8 languages and further analysis show that our method can effectively improve the E2E-ST performance and achieves an average BLEU of 29.0.</abstract>
<identifier type="citekey">zhang-etal-2022-fcgcl</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.222</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.222</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3048</start>
<end>3059</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FCGCL: Fine- and Coarse-Granularity Contrastive Learning for Speech Translation
%A Zhang, Hao
%A Si, Nianwen
%A Chen, Yaqi
%A Li, Zhen
%A Niu, Tong
%A Yang, Xukui
%A Qu, Dan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhang-etal-2022-fcgcl
%X It is notoriously difficult to implement end-to-end speech translation (E2E-ST) model because of the task complexity and data scarcity. Existing techniques often attempt to carry out implicit knowledge transfer from machine translation (MT) to ST model by imposing various constraints. However, in this transfer scenario, a significant problem is that the performance of the MT will drop significantly and the final transfer effect is also restricted. In this article, we recommend Fine and Coarse Granularity Contrastive Learning (FCGCL), which conduct explicit knowledge transfer from MT to ST model. Specially, we ensure through multi granularity contrastive learning that inputs with similar semantic between different modalities are encoded closely in the shared semantic space while inputs with different semantics are kept apart. Experiments on the MuST-C datasets on all 8 languages and further analysis show that our method can effectively improve the E2E-ST performance and achieves an average BLEU of 29.0.
%R 10.18653/v1/2022.findings-emnlp.222
%U https://aclanthology.org/2022.findings-emnlp.222
%U https://doi.org/10.18653/v1/2022.findings-emnlp.222
%P 3048-3059
Markdown (Informal)
[FCGCL: Fine- and Coarse-Granularity Contrastive Learning for Speech Translation](https://aclanthology.org/2022.findings-emnlp.222) (Zhang et al., Findings 2022)
ACL