<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nowakowski-jassem-2021-neural">
    <titleInfo>
        <title>Neural Machine Translation with Inflected Lexicon</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Artur</namePart>
        <namePart type="family">Nowakowski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Krzysztof</namePart>
        <namePart type="family">Jassem</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of Machine Translation Summit XVIII: Research Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Francisco</namePart>
            <namePart type="family">Guzmán</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Machine Translation in the Americas</publisher>
            <place>
                <placeTerm type="text">Virtual</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which handles the inflected forms of lexical entries and does not require any modification to the training data or model architecture. To evaluate its effectiveness and we carry out experiments in two different scenarios: general and domain-specific. We compare our method with baseline translation and i.e. translation without lexical constraints and in terms of translation speed and translation quality. To evaluate how well the method handles the constraints and we propose new evaluation metrics which take into account the presence and placement and duplication and inflectional correctness of lexical terms in the output sentence.</abstract>
    <identifier type="citekey">nowakowski-jassem-2021-neural</identifier>
    <location>
        <url>https://aclanthology.org/2021.mtsummit-research.23</url>
    </location>
    <part>
        <date>2021-08</date>
        <extent unit="page">
            <start>282</start>
            <end>292</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Neural Machine Translation with Inflected Lexicon
%A Nowakowski, Artur
%A Jassem, Krzysztof
%Y Duh, Kevin
%Y Guzmán, Francisco
%S Proceedings of Machine Translation Summit XVIII: Research Track
%D 2021
%8 August
%I Association for Machine Translation in the Americas
%C Virtual
%F nowakowski-jassem-2021-neural
%X The paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which handles the inflected forms of lexical entries and does not require any modification to the training data or model architecture. To evaluate its effectiveness and we carry out experiments in two different scenarios: general and domain-specific. We compare our method with baseline translation and i.e. translation without lexical constraints and in terms of translation speed and translation quality. To evaluate how well the method handles the constraints and we propose new evaluation metrics which take into account the presence and placement and duplication and inflectional correctness of lexical terms in the output sentence.
%U https://aclanthology.org/2021.mtsummit-research.23
%P 282-292

Markdown (Informal)

[Neural Machine Translation with Inflected Lexicon](https://aclanthology.org/2021.mtsummit-research.23) (Nowakowski & Jassem, MTSummit 2021)

• Neural Machine Translation with Inflected Lexicon (Nowakowski & Jassem, MTSummit 2021)

ACL

• Artur Nowakowski and Krzysztof Jassem. 2021. Neural Machine Translation with Inflected Lexicon. In Proceedings of Machine Translation Summit XVIII: Research Track, pages 282–292, Virtual. Association for Machine Translation in the Americas.