<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sokolov-etal-2012-non">
    <titleInfo>
        <title>Non-linear n-best List Reranking with Few Features</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Artem</namePart>
        <namePart type="family">Sokolov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guillaume</namePart>
        <namePart type="family">Wisniewski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Yvon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2012-oct 28-nov 1</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Machine Translation in the Americas</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In Machine Translation, it is customary to compute the model score of a predicted hypothesis as a linear combination of multiple features, where each feature assesses a particular facet of the hypothesis. The choice of a linear combination is usually justified by the possibility of efficient inference (decoding); yet, the appropriateness of this simple combination scheme to the task at hand is rarely questioned. In this paper, we propose an approach that replaces the linear scoring function with a non-linear scoring function. To investigate the applicability of this approach, we rescore n-best lists generated with a conventional machine translation engine (using a linear scoring function for generating its hypotheses) with a non-linear scoring function learned using the learning-to-rank framework. Moderate, though consistent, gains in BLEU are demonstrated on the WMT’10, WMT’11 and WMT’12 test sets.</abstract>
    <identifier type="citekey">sokolov-etal-2012-non</identifier>
    <location>
        <url>https://aclanthology.org/2012.amta-papers.17</url>
    </location>
    <part>
        <date>2012-oct 28-nov 1</date>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Non-linear n-best List Reranking with Few Features
%A Sokolov, Artem
%A Wisniewski, Guillaume
%A Yvon, François
%S Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers
%D 2012
%8 oct 28 nov 1
%I Association for Machine Translation in the Americas
%C San Diego, California, USA
%F sokolov-etal-2012-non
%X In Machine Translation, it is customary to compute the model score of a predicted hypothesis as a linear combination of multiple features, where each feature assesses a particular facet of the hypothesis. The choice of a linear combination is usually justified by the possibility of efficient inference (decoding); yet, the appropriateness of this simple combination scheme to the task at hand is rarely questioned. In this paper, we propose an approach that replaces the linear scoring function with a non-linear scoring function. To investigate the applicability of this approach, we rescore n-best lists generated with a conventional machine translation engine (using a linear scoring function for generating its hypotheses) with a non-linear scoring function learned using the learning-to-rank framework. Moderate, though consistent, gains in BLEU are demonstrated on the WMT’10, WMT’11 and WMT’12 test sets.
%U https://aclanthology.org/2012.amta-papers.17

Markdown (Informal)

[Non-linear n-best List Reranking with Few Features](https://aclanthology.org/2012.amta-papers.17) (Sokolov et al., AMTA 2012)

• Non-linear n-best List Reranking with Few Features (Sokolov et al., AMTA 2012)

ACL

• Artem Sokolov, Guillaume Wisniewski, and François Yvon. 2012. Non-linear n-best List Reranking with Few Features. In Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers, San Diego, California, USA. Association for Machine Translation in the Americas.