<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lampouras-vlachos-2016-imitation">
    <titleInfo>
        <title>Imitation learning for language generation from unaligned data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gerasimos</namePart>
        <namePart type="family">Lampouras</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andreas</namePart>
        <namePart type="family">Vlachos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yuji</namePart>
            <namePart type="family">Matsumoto</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rashmi</namePart>
            <namePart type="family">Prasad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>The COLING 2016 Organizing Committee</publisher>
            <place>
                <placeTerm type="text">Osaka, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Natural language generation (NLG) is the task of generating natural language from a meaning representation. Current rule-based approaches require domain-specific and manually constructed linguistic resources, while most machine-learning based approaches rely on aligned training data and/or phrase templates. The latter are needed to restrict the search space for the structured prediction task defined by the unaligned datasets. In this work we propose the use of imitation learning for structured prediction which learns an incremental model that handles the large search space by avoiding explicit enumeration of the outputs. We focus on the Locally Optimal Learning to Search framework which allows us to train against non-decomposable loss functions such as the BLEU or ROUGE scores while not assuming gold standard alignments. We evaluate our approach on three datasets using both automatic measures and human judgements and achieve results comparable to the state-of-the-art approaches developed for each of them.</abstract>
    <identifier type="citekey">lampouras-vlachos-2016-imitation</identifier>
    <location>
        <url>https://aclanthology.org/C16-1105</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>1101</start>
            <end>1112</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Imitation learning for language generation from unaligned data
%A Lampouras, Gerasimos
%A Vlachos, Andreas
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F lampouras-vlachos-2016-imitation
%X Natural language generation (NLG) is the task of generating natural language from a meaning representation. Current rule-based approaches require domain-specific and manually constructed linguistic resources, while most machine-learning based approaches rely on aligned training data and/or phrase templates. The latter are needed to restrict the search space for the structured prediction task defined by the unaligned datasets. In this work we propose the use of imitation learning for structured prediction which learns an incremental model that handles the large search space by avoiding explicit enumeration of the outputs. We focus on the Locally Optimal Learning to Search framework which allows us to train against non-decomposable loss functions such as the BLEU or ROUGE scores while not assuming gold standard alignments. We evaluate our approach on three datasets using both automatic measures and human judgements and achieve results comparable to the state-of-the-art approaches developed for each of them.
%U https://aclanthology.org/C16-1105
%P 1101-1112

Markdown (Informal)

[Imitation learning for language generation from unaligned data](https://aclanthology.org/C16-1105) (Lampouras & Vlachos, COLING 2016)

• Imitation learning for language generation from unaligned data (Lampouras & Vlachos, COLING 2016)

ACL

• Gerasimos Lampouras and Andreas Vlachos. 2016. Imitation learning for language generation from unaligned data. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1101–1112, Osaka, Japan. The COLING 2016 Organizing Committee.