@article{gritta-etal-2021-conversation,
title = "Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management",
author = "Gritta, Milan and
Lampouras, Gerasimos and
Iacobacci, Ignacio",
editor = "Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "9",
year = "2021",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2021.tacl-1.3",
doi = "10.1162/tacl_a_00352",
pages = "36--52",
abstract = "Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size con- sidering the complexity of the dialogues. Additionally, conventional training signal in- ference is not suitable for non-deterministic agent behavior, namely, considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents. ConvGraph generates novel dialogue paths to augment data volume and diversity. Intrinsic and extrinsic evaluation across three datasets shows that data augmentation and/or multi-reference training with ConvGraph can improve dialogue success rates by up to 6.4{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gritta-etal-2021-conversation">
<titleInfo>
<title>Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milan</namePart>
<namePart type="family">Gritta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Ignacio</namePart>
<namePart type="family">Iacobacci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size con- sidering the complexity of the dialogues. Additionally, conventional training signal in- ference is not suitable for non-deterministic agent behavior, namely, considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents. ConvGraph generates novel dialogue paths to augment data volume and diversity. Intrinsic and extrinsic evaluation across three datasets shows that data augmentation and/or multi-reference training with ConvGraph can improve dialogue success rates by up to 6.4%.</abstract>
<identifier type="citekey">gritta-etal-2021-conversation</identifier>
<identifier type="doi">10.1162/tacl_a_00352</identifier>
<location>
<url>https://aclanthology.org/2021.tacl-1.3</url>
</location>
<part>
<date>2021</date>
<detail type="volume"><number>9</number></detail>
<extent unit="page">
<start>36</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management
%A Gritta, Milan
%A Lampouras, Gerasimos
%A Iacobacci, Ignacio
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F gritta-etal-2021-conversation
%X Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size con- sidering the complexity of the dialogues. Additionally, conventional training signal in- ference is not suitable for non-deterministic agent behavior, namely, considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents. ConvGraph generates novel dialogue paths to augment data volume and diversity. Intrinsic and extrinsic evaluation across three datasets shows that data augmentation and/or multi-reference training with ConvGraph can improve dialogue success rates by up to 6.4%.
%R 10.1162/tacl_a_00352
%U https://aclanthology.org/2021.tacl-1.3
%U https://doi.org/10.1162/tacl_a_00352
%P 36-52
Markdown (Informal)
[Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management](https://aclanthology.org/2021.tacl-1.3) (Gritta et al., TACL 2021)
ACL