@inproceedings{wu-etal-2023-diacttod,
title = "{D}iact{TOD}: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems",
author = "Wu, Qingyang and
Gung, James and
Shu, Raphael and
Zhang, Yi",
editor = "Stoyanchev, Svetlana and
Joty, Shafiq and
Schlangen, David and
Dusek, Ondrej and
Kennington, Casey and
Alikhani, Malihe",
booktitle = "Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigdial-1.24",
doi = "10.18653/v1/2023.sigdial-1.24",
pages = "255--267",
abstract = "Dialogue act annotations are important to improve response generation quality in task-oriented dialogue systems. However, it can be challenging to use dialogue acts to control response generation in a generalizable way because different datasets and tasks may have incompatible annotations. While alternative methods that utilize latent action spaces or reinforcement learning do not require explicit annotations, they may lack interpretability or face difficulties defining task-specific rewards. In this work, we present a novel end-to-end latent dialogue act model (DiactTOD) that represents dialogue acts in a latent space. DiactTOD, when pre-trained on a large corpus, is able to predict and control dialogue acts to generate controllable responses using these latent representations in a zero-shot fashion. Our approach demonstrates state-of-the-art performance across a wide range of experimental settings on the MultiWOZ dataset, including zero-shot, few-shot, and full data fine-tuning with both end-to-end and policy optimization configurations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2023-diacttod">
<titleInfo>
<title>DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qingyang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Gung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Stoyanchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Dusek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czechia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue act annotations are important to improve response generation quality in task-oriented dialogue systems. However, it can be challenging to use dialogue acts to control response generation in a generalizable way because different datasets and tasks may have incompatible annotations. While alternative methods that utilize latent action spaces or reinforcement learning do not require explicit annotations, they may lack interpretability or face difficulties defining task-specific rewards. In this work, we present a novel end-to-end latent dialogue act model (DiactTOD) that represents dialogue acts in a latent space. DiactTOD, when pre-trained on a large corpus, is able to predict and control dialogue acts to generate controllable responses using these latent representations in a zero-shot fashion. Our approach demonstrates state-of-the-art performance across a wide range of experimental settings on the MultiWOZ dataset, including zero-shot, few-shot, and full data fine-tuning with both end-to-end and policy optimization configurations.</abstract>
<identifier type="citekey">wu-etal-2023-diacttod</identifier>
<identifier type="doi">10.18653/v1/2023.sigdial-1.24</identifier>
<location>
<url>https://aclanthology.org/2023.sigdial-1.24</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>255</start>
<end>267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems
%A Wu, Qingyang
%A Gung, James
%A Shu, Raphael
%A Zhang, Yi
%Y Stoyanchev, Svetlana
%Y Joty, Shafiq
%Y Schlangen, David
%Y Dusek, Ondrej
%Y Kennington, Casey
%Y Alikhani, Malihe
%S Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F wu-etal-2023-diacttod
%X Dialogue act annotations are important to improve response generation quality in task-oriented dialogue systems. However, it can be challenging to use dialogue acts to control response generation in a generalizable way because different datasets and tasks may have incompatible annotations. While alternative methods that utilize latent action spaces or reinforcement learning do not require explicit annotations, they may lack interpretability or face difficulties defining task-specific rewards. In this work, we present a novel end-to-end latent dialogue act model (DiactTOD) that represents dialogue acts in a latent space. DiactTOD, when pre-trained on a large corpus, is able to predict and control dialogue acts to generate controllable responses using these latent representations in a zero-shot fashion. Our approach demonstrates state-of-the-art performance across a wide range of experimental settings on the MultiWOZ dataset, including zero-shot, few-shot, and full data fine-tuning with both end-to-end and policy optimization configurations.
%R 10.18653/v1/2023.sigdial-1.24
%U https://aclanthology.org/2023.sigdial-1.24
%U https://doi.org/10.18653/v1/2023.sigdial-1.24
%P 255-267
Markdown (Informal)
[DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems](https://aclanthology.org/2023.sigdial-1.24) (Wu et al., SIGDIAL 2023)
ACL