@inproceedings{yoo-etal-2020-variational,
title = "Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation",
author = "Yoo, Kang Min and
Lee, Hanbit and
Dernoncourt, Franck and
Bui, Trung and
Chang, Walter and
Lee, Sang-goo",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.274",
doi = "10.18653/v1/2020.emnlp-main.274",
pages = "3406--3425",
abstract = "Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks. In this work, we extend this approach to the task of dialog state tracking for goaloriented dialogs. Due to the inherent hierarchical structure of goal-oriented dialogs over utterances and related annotations, the deep generative model must be capable of capturing the coherence among different hierarchies and types of dialog features. We propose the Variational Hierarchical Dialog Autoencoder (VHDA) for modeling the complete aspects of goal-oriented dialogs, including linguistic features and underlying structured annotations, namely speaker information, dialog acts, and goals. The proposed architecture is designed to model each aspect of goal-oriented dialogs using inter-connected latent variables and learns to generate coherent goal-oriented dialogs from the latent spaces. To overcome training issues that arise from training complex variational models, we propose appropriate training strategies. Experiments on various dialog datasets show that our model improves the downstream dialog trackers{'} robustness via generative data augmentation. We also discover additional benefits of our unified approach to modeling goal-oriented dialogs {--} dialog response generation and user simulation, where our model outperforms previous strong baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoo-etal-2020-variational">
<titleInfo>
<title>Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="given">Min</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanbit</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sang-goo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks. In this work, we extend this approach to the task of dialog state tracking for goaloriented dialogs. Due to the inherent hierarchical structure of goal-oriented dialogs over utterances and related annotations, the deep generative model must be capable of capturing the coherence among different hierarchies and types of dialog features. We propose the Variational Hierarchical Dialog Autoencoder (VHDA) for modeling the complete aspects of goal-oriented dialogs, including linguistic features and underlying structured annotations, namely speaker information, dialog acts, and goals. The proposed architecture is designed to model each aspect of goal-oriented dialogs using inter-connected latent variables and learns to generate coherent goal-oriented dialogs from the latent spaces. To overcome training issues that arise from training complex variational models, we propose appropriate training strategies. Experiments on various dialog datasets show that our model improves the downstream dialog trackers’ robustness via generative data augmentation. We also discover additional benefits of our unified approach to modeling goal-oriented dialogs – dialog response generation and user simulation, where our model outperforms previous strong baselines.</abstract>
<identifier type="citekey">yoo-etal-2020-variational</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.274</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.274</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3406</start>
<end>3425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation
%A Yoo, Kang Min
%A Lee, Hanbit
%A Dernoncourt, Franck
%A Bui, Trung
%A Chang, Walter
%A Lee, Sang-goo
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F yoo-etal-2020-variational
%X Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks. In this work, we extend this approach to the task of dialog state tracking for goaloriented dialogs. Due to the inherent hierarchical structure of goal-oriented dialogs over utterances and related annotations, the deep generative model must be capable of capturing the coherence among different hierarchies and types of dialog features. We propose the Variational Hierarchical Dialog Autoencoder (VHDA) for modeling the complete aspects of goal-oriented dialogs, including linguistic features and underlying structured annotations, namely speaker information, dialog acts, and goals. The proposed architecture is designed to model each aspect of goal-oriented dialogs using inter-connected latent variables and learns to generate coherent goal-oriented dialogs from the latent spaces. To overcome training issues that arise from training complex variational models, we propose appropriate training strategies. Experiments on various dialog datasets show that our model improves the downstream dialog trackers’ robustness via generative data augmentation. We also discover additional benefits of our unified approach to modeling goal-oriented dialogs – dialog response generation and user simulation, where our model outperforms previous strong baselines.
%R 10.18653/v1/2020.emnlp-main.274
%U https://aclanthology.org/2020.emnlp-main.274
%U https://doi.org/10.18653/v1/2020.emnlp-main.274
%P 3406-3425
Markdown (Informal)
[Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation](https://aclanthology.org/2020.emnlp-main.274) (Yoo et al., EMNLP 2020)
ACL