@inproceedings{parida-etal-2021-multimodal,
title = "Multimodal Neural Machine Translation System for {E}nglish to {B}engali",
author = "Parida, Shantipriya and
Panda, Subhadarshi and
Biswal, Satya Prakash and
Kotwal, Ketan and
Sen, Arghyadeep and
Dash, Satya Ranjan and
Motlicek, Petr",
editor = "Doren Singh, Thoudam and
Espa{\~n}a i Bonet, Cristina and
Bandyopadhyay, Sivaji and
van Genabith, Josef",
booktitle = "Proceedings of the First Workshop on Multimodal Machine Translation for Low Resource Languages (MMTLRL 2021)",
month = sep,
year = "2021",
address = "Online (Virtual Mode)",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.mmtlrl-1.6/",
pages = "31--39",
abstract = "Multimodal Machine Translation (MMT) systems utilize additional information from other modalities beyond text to improve the quality of machine translation (MT). The additional modality is typically in the form of images. Despite proven advantages, it is indeed difficult to develop an MMT system for various languages primarily due to the lack of a suitable multimodal dataset. In this work, we develop an MMT for English-{\ensuremath{>}} Bengali using a recently published Bengali Visual Genome (BVG) dataset that contains images with associated bilingual textual descriptions. Through a comparative study of the developed MMT system vis-a-vis a Text-to-text translation, we demonstrate that the use of multimodal data not only improves the translation performance improvement in BLEU score of +1.3 on the development set, +3.9 on the evaluation test, and +0.9 on the challenge test set but also helps to resolve ambiguities in the pure text description. As per best of our knowledge, our English-Bengali MMT system is the first attempt in this direction, and thus, can act as a baseline for the subsequent research in MMT for low resource languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parida-etal-2021-multimodal">
<titleInfo>
<title>Multimodal Neural Machine Translation System for English to Bengali</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shantipriya</namePart>
<namePart type="family">Parida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subhadarshi</namePart>
<namePart type="family">Panda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satya</namePart>
<namePart type="given">Prakash</namePart>
<namePart type="family">Biswal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ketan</namePart>
<namePart type="family">Kotwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arghyadeep</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satya</namePart>
<namePart type="given">Ranjan</namePart>
<namePart type="family">Dash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Motlicek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Multimodal Machine Translation for Low Resource Languages (MMTLRL 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thoudam</namePart>
<namePart type="family">Doren Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">España i Bonet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">van Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Online (Virtual Mode)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal Machine Translation (MMT) systems utilize additional information from other modalities beyond text to improve the quality of machine translation (MT). The additional modality is typically in the form of images. Despite proven advantages, it is indeed difficult to develop an MMT system for various languages primarily due to the lack of a suitable multimodal dataset. In this work, we develop an MMT for English-\ensuremath> Bengali using a recently published Bengali Visual Genome (BVG) dataset that contains images with associated bilingual textual descriptions. Through a comparative study of the developed MMT system vis-a-vis a Text-to-text translation, we demonstrate that the use of multimodal data not only improves the translation performance improvement in BLEU score of +1.3 on the development set, +3.9 on the evaluation test, and +0.9 on the challenge test set but also helps to resolve ambiguities in the pure text description. As per best of our knowledge, our English-Bengali MMT system is the first attempt in this direction, and thus, can act as a baseline for the subsequent research in MMT for low resource languages.</abstract>
<identifier type="citekey">parida-etal-2021-multimodal</identifier>
<location>
<url>https://aclanthology.org/2021.mmtlrl-1.6/</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>31</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Neural Machine Translation System for English to Bengali
%A Parida, Shantipriya
%A Panda, Subhadarshi
%A Biswal, Satya Prakash
%A Kotwal, Ketan
%A Sen, Arghyadeep
%A Dash, Satya Ranjan
%A Motlicek, Petr
%Y Doren Singh, Thoudam
%Y España i Bonet, Cristina
%Y Bandyopadhyay, Sivaji
%Y van Genabith, Josef
%S Proceedings of the First Workshop on Multimodal Machine Translation for Low Resource Languages (MMTLRL 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Online (Virtual Mode)
%F parida-etal-2021-multimodal
%X Multimodal Machine Translation (MMT) systems utilize additional information from other modalities beyond text to improve the quality of machine translation (MT). The additional modality is typically in the form of images. Despite proven advantages, it is indeed difficult to develop an MMT system for various languages primarily due to the lack of a suitable multimodal dataset. In this work, we develop an MMT for English-\ensuremath> Bengali using a recently published Bengali Visual Genome (BVG) dataset that contains images with associated bilingual textual descriptions. Through a comparative study of the developed MMT system vis-a-vis a Text-to-text translation, we demonstrate that the use of multimodal data not only improves the translation performance improvement in BLEU score of +1.3 on the development set, +3.9 on the evaluation test, and +0.9 on the challenge test set but also helps to resolve ambiguities in the pure text description. As per best of our knowledge, our English-Bengali MMT system is the first attempt in this direction, and thus, can act as a baseline for the subsequent research in MMT for low resource languages.
%U https://aclanthology.org/2021.mmtlrl-1.6/
%P 31-39
Markdown (Informal)
[Multimodal Neural Machine Translation System for English to Bengali](https://aclanthology.org/2021.mmtlrl-1.6/) (Parida et al., MMTLRL 2021)
ACL
- Shantipriya Parida, Subhadarshi Panda, Satya Prakash Biswal, Ketan Kotwal, Arghyadeep Sen, Satya Ranjan Dash, and Petr Motlicek. 2021. Multimodal Neural Machine Translation System for English to Bengali. In Proceedings of the First Workshop on Multimodal Machine Translation for Low Resource Languages (MMTLRL 2021), pages 31–39, Online (Virtual Mode). INCOMA Ltd..