<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lowe-etal-2017-training">
    <titleInfo>
        <title>Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ryan</namePart>
        <namePart type="family">Lowe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nissan</namePart>
        <namePart type="family">Pow</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Iulian</namePart>
        <namePart type="given">Vlad</namePart>
        <namePart type="family">Serban</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Laurent</namePart>
        <namePart type="family">Charlin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chia-Wei</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joelle</namePart>
        <namePart type="family">Pineau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Dialogue &amp; Discourse</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>University of Bielefeld</publisher>
            <place>
                <placeTerm type="text">Bielefeld, Germany</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>In this paper, we construct and train end-to-end neural network-based dialogue systems usingan updated version of the recent Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This dataset is interesting because of its size, long context lengths, and technical nature; thus, it can be used to train large models directly from data with minimal feature engineering, which can be both time consuming and expensive. We provide baselines in two different environments: one where models are trained to maximize the log-likelihood of a generated utterance conditioned on the context of the conversation, and one where models are trained to select the correct next response from a list of candidate responses. These are both evaluated on a recall task that we call Next Utterance Classification (NUC), as well as other generation-specific metrics. Finally, we provide a qualitative error analysis to help determine the most promising directions for future research on the Ubuntu Dialogue Corpus, and for end-to-end dialogue systems in general.</abstract>
    <identifier type="citekey">lowe-etal-2017-training</identifier>
    <identifier type="doi">10.5087/dad.2017.102</identifier>
    <location>
        <url>https://aclanthology.org/2017.dnd-8.14/</url>
    </location>
    <part>
        <date>2017-01</date>
        <detail type="volume"><number>8</number></detail>
        <extent unit="page">
            <start>31</start>
            <end>65</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus
%A Lowe, Ryan
%A Pow, Nissan
%A Serban, Iulian Vlad
%A Charlin, Laurent
%A Liu, Chia-Wei
%A Pineau, Joelle
%J Dialogue & Discourse
%D 2017
%8 January
%V 8
%I University of Bielefeld
%C Bielefeld, Germany
%F lowe-etal-2017-training
%X In this paper, we construct and train end-to-end neural network-based dialogue systems usingan updated version of the recent Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This dataset is interesting because of its size, long context lengths, and technical nature; thus, it can be used to train large models directly from data with minimal feature engineering, which can be both time consuming and expensive. We provide baselines in two different environments: one where models are trained to maximize the log-likelihood of a generated utterance conditioned on the context of the conversation, and one where models are trained to select the correct next response from a list of candidate responses. These are both evaluated on a recall task that we call Next Utterance Classification (NUC), as well as other generation-specific metrics. Finally, we provide a qualitative error analysis to help determine the most promising directions for future research on the Ubuntu Dialogue Corpus, and for end-to-end dialogue systems in general.
%R 10.5087/dad.2017.102
%U https://aclanthology.org/2017.dnd-8.14/
%U https://doi.org/10.5087/dad.2017.102
%P 31-65

Markdown (Informal)

[Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus](https://aclanthology.org/2017.dnd-8.14/) (Lowe et al., DND 2017)

• Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus (Lowe et al., DND 2017)

ACL

• Ryan Lowe, Nissan Pow, Iulian Vlad Serban, Laurent Charlin, Chia-Wei Liu, and Joelle Pineau. 2017. Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus. Dialogue & Discourse, 8:31–65.