@inproceedings{ji-etal-2022-increasing,
title = "Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective",
author = "Ji, Baijun and
Zhang, Tong and
Zou, Yicheng and
Hu, Bojie and
Shen, Si",
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.453",
doi = "10.18653/v1/2022.emnlp-main.453",
pages = "6755--6764",
abstract = "Multimodal machine translation (MMT) aims to improve translation quality by equipping the source sentence with its corresponding image. Despite the promising performance, MMT models still suffer the problem of input degradation: models focus more on textual information while visual information is generally overlooked. In this paper, we endeavor to improve MMT performance by increasing visual awareness from an information theoretic perspective. In detail, we decompose the informative visual signals into two parts: source-specific information and target-specific information. We use mutual information to quantify them and propose two methods for objective optimization to better leverage visual signals. Experiments on two datasets demonstrate that our approach can effectively enhance the visual awareness of MMT model and achieve superior results against strong baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ji-etal-2022-increasing">
<titleInfo>
<title>Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Baijun</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yicheng</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bojie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si</namePart>
<namePart type="family">Shen</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>Multimodal machine translation (MMT) aims to improve translation quality by equipping the source sentence with its corresponding image. Despite the promising performance, MMT models still suffer the problem of input degradation: models focus more on textual information while visual information is generally overlooked. In this paper, we endeavor to improve MMT performance by increasing visual awareness from an information theoretic perspective. In detail, we decompose the informative visual signals into two parts: source-specific information and target-specific information. We use mutual information to quantify them and propose two methods for objective optimization to better leverage visual signals. Experiments on two datasets demonstrate that our approach can effectively enhance the visual awareness of MMT model and achieve superior results against strong baselines.</abstract>
<identifier type="citekey">ji-etal-2022-increasing</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.453</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.453</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6755</start>
<end>6764</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective
%A Ji, Baijun
%A Zhang, Tong
%A Zou, Yicheng
%A Hu, Bojie
%A Shen, Si
%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 ji-etal-2022-increasing
%X Multimodal machine translation (MMT) aims to improve translation quality by equipping the source sentence with its corresponding image. Despite the promising performance, MMT models still suffer the problem of input degradation: models focus more on textual information while visual information is generally overlooked. In this paper, we endeavor to improve MMT performance by increasing visual awareness from an information theoretic perspective. In detail, we decompose the informative visual signals into two parts: source-specific information and target-specific information. We use mutual information to quantify them and propose two methods for objective optimization to better leverage visual signals. Experiments on two datasets demonstrate that our approach can effectively enhance the visual awareness of MMT model and achieve superior results against strong baselines.
%R 10.18653/v1/2022.emnlp-main.453
%U https://aclanthology.org/2022.emnlp-main.453
%U https://doi.org/10.18653/v1/2022.emnlp-main.453
%P 6755-6764
Markdown (Informal)
[Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective](https://aclanthology.org/2022.emnlp-main.453) (Ji et al., EMNLP 2022)
ACL