@inproceedings{peng-etal-2022-distill,
title = "Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation",
author = "Peng, Ru and
Zeng, Yawen and
Zhao, Jake",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.152",
doi = "10.18653/v1/2022.emnlp-main.152",
pages = "2379--2390",
abstract = "Past works on multimodal machine translation (MMT) elevate bilingual setup by incorporating additional aligned vision information.However, an image-must requirement of the multimodal dataset largely hinders MMT{'}s development {---} namely that it demands an aligned form of [image, source text, target text].This limitation is generally troublesome during the inference phase especially when the aligned image is not provided as in the normal NMT setup.Thus, in this work, we introduce IKD-MMT, a novel MMT framework to support the image-free inference phase via an inversion knowledge distillation scheme.In particular, a multimodal feature generator is executed with a knowledge distillation module, which directly generates the multimodal feature from (only) source texts as the input.While there have been a few prior works entertaining the possibility to support image-free inference for machine translation, their performances have yet to rival the image-must translation.In our experiments, we identify our method as the first image-free approach to comprehensively rival or even surpass (almost) all image-must frameworks, and achieved the state-of-the-art result on the often-used Multi30k benchmark. Our code and data are availableat: https://github.com/pengr/IKD-mmt/tree/master..",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-etal-2022-distill">
<titleInfo>
<title>Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ru</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yawen</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jake</namePart>
<namePart type="family">Zhao</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>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</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>Past works on multimodal machine translation (MMT) elevate bilingual setup by incorporating additional aligned vision information.However, an image-must requirement of the multimodal dataset largely hinders MMT’s development — namely that it demands an aligned form of [image, source text, target text].This limitation is generally troublesome during the inference phase especially when the aligned image is not provided as in the normal NMT setup.Thus, in this work, we introduce IKD-MMT, a novel MMT framework to support the image-free inference phase via an inversion knowledge distillation scheme.In particular, a multimodal feature generator is executed with a knowledge distillation module, which directly generates the multimodal feature from (only) source texts as the input.While there have been a few prior works entertaining the possibility to support image-free inference for machine translation, their performances have yet to rival the image-must translation.In our experiments, we identify our method as the first image-free approach to comprehensively rival or even surpass (almost) all image-must frameworks, and achieved the state-of-the-art result on the often-used Multi30k benchmark. Our code and data are availableat: https://github.com/pengr/IKD-mmt/tree/master..</abstract>
<identifier type="citekey">peng-etal-2022-distill</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.152</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.152</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>2379</start>
<end>2390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation
%A Peng, Ru
%A Zeng, Yawen
%A Zhao, Jake
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F peng-etal-2022-distill
%X Past works on multimodal machine translation (MMT) elevate bilingual setup by incorporating additional aligned vision information.However, an image-must requirement of the multimodal dataset largely hinders MMT’s development — namely that it demands an aligned form of [image, source text, target text].This limitation is generally troublesome during the inference phase especially when the aligned image is not provided as in the normal NMT setup.Thus, in this work, we introduce IKD-MMT, a novel MMT framework to support the image-free inference phase via an inversion knowledge distillation scheme.In particular, a multimodal feature generator is executed with a knowledge distillation module, which directly generates the multimodal feature from (only) source texts as the input.While there have been a few prior works entertaining the possibility to support image-free inference for machine translation, their performances have yet to rival the image-must translation.In our experiments, we identify our method as the first image-free approach to comprehensively rival or even surpass (almost) all image-must frameworks, and achieved the state-of-the-art result on the often-used Multi30k benchmark. Our code and data are availableat: https://github.com/pengr/IKD-mmt/tree/master..
%R 10.18653/v1/2022.emnlp-main.152
%U https://aclanthology.org/2022.emnlp-main.152
%U https://doi.org/10.18653/v1/2022.emnlp-main.152
%P 2379-2390
Markdown (Informal)
[Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation](https://aclanthology.org/2022.emnlp-main.152) (Peng et al., EMNLP 2022)
ACL