<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stojanovski-fraser-2018-coreference">
    <titleInfo>
        <title>Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dario</namePart>
        <namePart type="family">Stojanovski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Fraser</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Conference on Machine Translation: Research Papers</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Cross-sentence context can provide valuable information in Machine Translation and is critical for translation of anaphoric pronouns and for providing consistent translations. In this paper, we devise simple oracle experiments targeting coreference and coherence. Oracles are an easy way to evaluate the effect of different discourse-level phenomena in NMT using BLEU and eliminate the necessity to manually define challenge sets for this purpose. We propose two context-aware NMT models and compare them against models working on a concatenation of consecutive sentences. Concatenation models perform better, but are computationally expensive. We show that NMT models taking advantage of context oracle signals can achieve considerable gains in BLEU, of up to 7.02 BLEU for coreference and 1.89 BLEU for coherence on subtitles translation. Access to strong signals allows us to make clear comparisons between context-aware models.</abstract>
    <identifier type="citekey">stojanovski-fraser-2018-coreference</identifier>
    <identifier type="doi">10.18653/v1/W18-6306</identifier>
    <location>
        <url>https://aclanthology.org/W18-6306</url>
    </location>
    <part>
        <date>2018-oct</date>
        <extent unit="page">
            <start>49</start>
            <end>60</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments
%A Stojanovski, Dario
%A Fraser, Alexander
%S Proceedings of the Third Conference on Machine Translation: Research Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Brussels, Belgium
%F stojanovski-fraser-2018-coreference
%X Cross-sentence context can provide valuable information in Machine Translation and is critical for translation of anaphoric pronouns and for providing consistent translations. In this paper, we devise simple oracle experiments targeting coreference and coherence. Oracles are an easy way to evaluate the effect of different discourse-level phenomena in NMT using BLEU and eliminate the necessity to manually define challenge sets for this purpose. We propose two context-aware NMT models and compare them against models working on a concatenation of consecutive sentences. Concatenation models perform better, but are computationally expensive. We show that NMT models taking advantage of context oracle signals can achieve considerable gains in BLEU, of up to 7.02 BLEU for coreference and 1.89 BLEU for coherence on subtitles translation. Access to strong signals allows us to make clear comparisons between context-aware models.
%R 10.18653/v1/W18-6306
%U https://aclanthology.org/W18-6306
%U https://doi.org/10.18653/v1/W18-6306
%P 49-60

Markdown (Informal)

[Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments](https://aclanthology.org/W18-6306) (Stojanovski & Fraser, 2018)

• Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments (Stojanovski & Fraser, 2018)

ACL

• Dario Stojanovski and Alexander Fraser. 2018. Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 49–60, Brussels, Belgium. Association for Computational Linguistics.