<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2018-self">
    <titleInfo>
        <title>Self-Learning Architecture for Natural Language Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hyungtak</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Siddarth</namePart>
        <namePart type="family">K.M.</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haehun</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Heesik</namePart>
        <namePart type="family">Jeon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Inchul</namePart>
        <namePart type="family">Hwang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jihie</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 11th International Conference on Natural Language Generation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Tilburg University, The Netherlands</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we propose a self-learning architecture for generating natural language templates for conversational assistants. Generating templates to cover all the combinations of slots in an intent is time consuming and labor-intensive. We examine three different models based on our proposed architecture - Rule-based model, Sequence-to-Sequence (Seq2Seq) model and Semantically Conditioned LSTM (SC-LSTM) model for the IoT domain - to reduce the human labor required for template generation. We demonstrate the feasibility of template generation for the IoT domain using our self-learning architecture. In both automatic and human evaluation, the self-learning architecture outperforms previous works trained with a fully human-labeled dataset. This is promising for commercial conversational assistant solutions.</abstract>
    <identifier type="citekey">choi-etal-2018-self</identifier>
    <identifier type="doi">10.18653/v1/W18-6520</identifier>
    <location>
        <url>https://aclanthology.org/W18-6520</url>
    </location>
    <part>
        <date>2018-nov</date>
        <extent unit="page">
            <start>165</start>
            <end>170</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-Learning Architecture for Natural Language Generation
%A Choi, Hyungtak
%A K.M., Siddarth
%A Yang, Haehun
%A Jeon, Heesik
%A Hwang, Inchul
%A Kim, Jihie
%S Proceedings of the 11th International Conference on Natural Language Generation
%D 2018
%8 nov
%I Association for Computational Linguistics
%C Tilburg University, The Netherlands
%F choi-etal-2018-self
%X In this paper, we propose a self-learning architecture for generating natural language templates for conversational assistants. Generating templates to cover all the combinations of slots in an intent is time consuming and labor-intensive. We examine three different models based on our proposed architecture - Rule-based model, Sequence-to-Sequence (Seq2Seq) model and Semantically Conditioned LSTM (SC-LSTM) model for the IoT domain - to reduce the human labor required for template generation. We demonstrate the feasibility of template generation for the IoT domain using our self-learning architecture. In both automatic and human evaluation, the self-learning architecture outperforms previous works trained with a fully human-labeled dataset. This is promising for commercial conversational assistant solutions.
%R 10.18653/v1/W18-6520
%U https://aclanthology.org/W18-6520
%U https://doi.org/10.18653/v1/W18-6520
%P 165-170

Markdown (Informal)

[Self-Learning Architecture for Natural Language Generation](https://aclanthology.org/W18-6520) (Choi et al., 2018)

• Self-Learning Architecture for Natural Language Generation (Choi et al., 2018)

ACL

• Hyungtak Choi, Siddarth K.M., Haehun Yang, Heesik Jeon, Inchul Hwang, and Jihie Kim. 2018. Self-Learning Architecture for Natural Language Generation. In Proceedings of the 11th International Conference on Natural Language Generation, pages 165–170, Tilburg University, The Netherlands. Association for Computational Linguistics.