<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mhaskar-bhattacharyya-2021-pivot">
    <titleInfo>
        <title>Pivot Based Transfer Learning for Neural Machine Translation: CFILT IITB @ WMT 2021 Triangular MT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shivam</namePart>
        <namePart type="family">Mhaskar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pushpak</namePart>
        <namePart type="family">Bhattacharyya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Sixth Conference on Machine Translation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we discuss the various techniques that we used to implement the Russian-Chinese machine translation system for the Triangular MT task at WMT 2021. Neural Machine translation systems based on transformer architecture have an encoder-decoder architecture, which are trained end-to-end and require a large amount of parallel corpus to produce good quality translations. This is the reason why neural machine translation systems are referred to as data hungry. Such a large amount of parallel corpus is majorly available for language pairs which include English and not for non-English language pairs. This is a major problem in building neural machine translation systems for non-English language pairs. We try to utilize the resources of the English language to improve the translation of non-English language pairs. We use the pivot language, that is English, to leverage transfer learning to improve the quality of Russian-Chinese translation. Compared to the baseline transformer-based neural machine translation system, we observe that the pivot language-based transfer learning technique gives a higher BLEU score.</abstract>
    <identifier type="citekey">mhaskar-bhattacharyya-2021-pivot</identifier>
    <location>
        <url>https://aclanthology.org/2021.wmt-1.39</url>
    </location>
    <part>
        <date>2021-nov</date>
        <extent unit="page">
            <start>336</start>
            <end>340</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Pivot Based Transfer Learning for Neural Machine Translation: CFILT IITB @ WMT 2021 Triangular MT
%A Mhaskar, Shivam
%A Bhattacharyya, Pushpak
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F mhaskar-bhattacharyya-2021-pivot
%X In this paper, we discuss the various techniques that we used to implement the Russian-Chinese machine translation system for the Triangular MT task at WMT 2021. Neural Machine translation systems based on transformer architecture have an encoder-decoder architecture, which are trained end-to-end and require a large amount of parallel corpus to produce good quality translations. This is the reason why neural machine translation systems are referred to as data hungry. Such a large amount of parallel corpus is majorly available for language pairs which include English and not for non-English language pairs. This is a major problem in building neural machine translation systems for non-English language pairs. We try to utilize the resources of the English language to improve the translation of non-English language pairs. We use the pivot language, that is English, to leverage transfer learning to improve the quality of Russian-Chinese translation. Compared to the baseline transformer-based neural machine translation system, we observe that the pivot language-based transfer learning technique gives a higher BLEU score.
%U https://aclanthology.org/2021.wmt-1.39
%P 336-340

Markdown (Informal)

[Pivot Based Transfer Learning for Neural Machine Translation: CFILT IITB @ WMT 2021 Triangular MT](https://aclanthology.org/2021.wmt-1.39) (Mhaskar & Bhattacharyya, WMT 2021)

• Pivot Based Transfer Learning for Neural Machine Translation: CFILT IITB @ WMT 2021 Triangular MT (Mhaskar & Bhattacharyya, WMT 2021)

ACL

• Shivam Mhaskar and Pushpak Bhattacharyya. 2021. Pivot Based Transfer Learning for Neural Machine Translation: CFILT IITB @ WMT 2021 Triangular MT. In Proceedings of the Sixth Conference on Machine Translation, pages 336–340, Online. Association for Computational Linguistics.