<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bawden-2017-machine-translation">
    <titleInfo>
        <title>Machine Translation of Speech-Like Texts: Strategies for the Inclusion of Context</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rachel</namePart>
        <namePart type="family">Bawden</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Actes des 24ème Conférence sur le Traitement Automatique des Langues Naturelles. 19es REncontres jeunes Chercheurs en Informatique pour le TAL (RECITAL 2017)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Iris</namePart>
            <namePart type="family">Eshkol-Taravella</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jean-Yves</namePart>
            <namePart type="family">Antoine</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ATALA</publisher>
            <place>
                <placeTerm type="text">Orléans, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Whilst the focus of Machine Translation (MT) has for a long time been the translation of planned, written texts, more and more research is being dedicated to translating speech-like texts (informal or spontaneous discourse or dialogue). To achieve high quality and natural translation of speechlike texts, the integration of context is needed, whether it is extra-linguistic (speaker identity, the interaction between speaker and interlocutor) or linguistic (coreference and stylistic phenomena linked to the spontaneous and informal nature of the texts). However, the integration of contextual information in MT systems remains limited in most current systems. In this paper, we present and critique three experiments for the integration of context into a MT system, each focusing on a different type of context and exploiting a different method: adaptation to speaker gender, cross-lingual pronoun prediction and the generation of tag questions from French into English.</abstract>
    <identifier type="citekey">bawden-2017-machine-translation</identifier>
    <location>
        <url>https://aclanthology.org/2017.jeptalnrecital-recital.1</url>
    </location>
    <part>
        <date>2017-6</date>
        <extent unit="page">
            <start>1</start>
            <end>14</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Machine Translation of Speech-Like Texts: Strategies for the Inclusion of Context
%A Bawden, Rachel
%Y Eshkol-Taravella, Iris
%Y Antoine, Jean-Yves
%S Actes des 24ème Conférence sur le Traitement Automatique des Langues Naturelles. 19es REncontres jeunes Chercheurs en Informatique pour le TAL (RECITAL 2017)
%D 2017
%8 June
%I ATALA
%C Orléans, France
%F bawden-2017-machine-translation
%X Whilst the focus of Machine Translation (MT) has for a long time been the translation of planned, written texts, more and more research is being dedicated to translating speech-like texts (informal or spontaneous discourse or dialogue). To achieve high quality and natural translation of speechlike texts, the integration of context is needed, whether it is extra-linguistic (speaker identity, the interaction between speaker and interlocutor) or linguistic (coreference and stylistic phenomena linked to the spontaneous and informal nature of the texts). However, the integration of contextual information in MT systems remains limited in most current systems. In this paper, we present and critique three experiments for the integration of context into a MT system, each focusing on a different type of context and exploiting a different method: adaptation to speaker gender, cross-lingual pronoun prediction and the generation of tag questions from French into English.
%U https://aclanthology.org/2017.jeptalnrecital-recital.1
%P 1-14

Markdown (Informal)

[Machine Translation of Speech-Like Texts: Strategies for the Inclusion of Context](https://aclanthology.org/2017.jeptalnrecital-recital.1) (Bawden, JEP/TALN/RECITAL 2017)

• Machine Translation of Speech-Like Texts: Strategies for the Inclusion of Context (Bawden, JEP/TALN/RECITAL 2017)

ACL

• Rachel Bawden. 2017. Machine Translation of Speech-Like Texts: Strategies for the Inclusion of Context. In Actes des 24ème Conférence sur le Traitement Automatique des Langues Naturelles. 19es REncontres jeunes Chercheurs en Informatique pour le TAL (RECITAL 2017), pages 1–14, Orléans, France. ATALA.