<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarwar-etal-2019-multi">
    <titleInfo>
        <title>A Multi-Task Architecture on Relevance-based Neural Query Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sheikh</namePart>
        <namePart type="given">Muhammad</namePart>
        <namePart type="family">Sarwar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hamed</namePart>
        <namePart type="family">Bonab</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="family">Allan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-jul</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We describe a multi-task learning approach to train a Neural Machine Translation (NMT) model with a Relevance-based Auxiliary Task (RAT) for search query translation. The translation process for Cross-lingual Information Retrieval (CLIR) task is usually treated as a black box and it is performed as an independent step. However, an NMT model trained on sentence-level parallel data is not aware of the vocabulary distribution of the retrieval corpus. We address this problem and propose a multi-task learning architecture that achieves 16% improvement over a strong baseline on Italian-English query-document dataset. We show using both quantitative and qualitative analysis that our model generates balanced and precise translations with the regularization effect it achieves from multi-task learning paradigm.</abstract>
    <identifier type="citekey">sarwar-etal-2019-multi</identifier>
    <identifier type="doi">10.18653/v1/P19-1639</identifier>
    <location>
        <url>https://aclanthology.org/P19-1639</url>
    </location>
    <part>
        <date>2019-jul</date>
        <extent unit="page">
            <start>6339</start>
            <end>6344</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Multi-Task Architecture on Relevance-based Neural Query Translation
%A Sarwar, Sheikh Muhammad
%A Bonab, Hamed
%A Allan, James
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 jul
%I Association for Computational Linguistics
%C Florence, Italy
%F sarwar-etal-2019-multi
%X We describe a multi-task learning approach to train a Neural Machine Translation (NMT) model with a Relevance-based Auxiliary Task (RAT) for search query translation. The translation process for Cross-lingual Information Retrieval (CLIR) task is usually treated as a black box and it is performed as an independent step. However, an NMT model trained on sentence-level parallel data is not aware of the vocabulary distribution of the retrieval corpus. We address this problem and propose a multi-task learning architecture that achieves 16% improvement over a strong baseline on Italian-English query-document dataset. We show using both quantitative and qualitative analysis that our model generates balanced and precise translations with the regularization effect it achieves from multi-task learning paradigm.
%R 10.18653/v1/P19-1639
%U https://aclanthology.org/P19-1639
%U https://doi.org/10.18653/v1/P19-1639
%P 6339-6344

Markdown (Informal)

[A Multi-Task Architecture on Relevance-based Neural Query Translation](https://aclanthology.org/P19-1639) (Sarwar et al., ACL 2019)

• A Multi-Task Architecture on Relevance-based Neural Query Translation (Sarwar et al., ACL 2019)

ACL

• Sheikh Muhammad Sarwar, Hamed Bonab, and James Allan. 2019. A Multi-Task Architecture on Relevance-based Neural Query Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6339–6344, Florence, Italy. Association for Computational Linguistics.