@inproceedings{lin-etal-2021-domain,
title = "Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems",
author = "Lin, Hsien-chin and
Lubis, Nurul and
Hu, Songbo and
van Niekerk, Carel and
Geishauser, Christian and
Heck, Michael and
Feng, Shutong and
Gasic, Milica",
editor = "Li, Haizhou and
Levow, Gina-Anne and
Yu, Zhou and
Gupta, Chitralekha and
Sisman, Berrak and
Cai, Siqi and
Vandyke, David and
Dethlefs, Nina and
Wu, Yan and
Li, Junyi Jessy",
booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2021",
address = "Singapore and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigdial-1.47",
doi = "10.18653/v1/2021.sigdial-1.47",
pages = "445--456",
abstract = "Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many set-ups therefore rely on a user simulator instead of humans. These user simulators have their own problems. While hand-coded, rule-based user simulators have been shown to be sufficient in small, simple domains, for complex domains the number of rules quickly becomes intractable. State-of-the-art data-driven user simulators, on the other hand, are still domain-dependent. This means that adaptation to each new domain requires redesigning and retraining. In this work, we propose a domain-independent transformer-based user simulator (TUS). The structure of TUS is not tied to a specific domain, enabling domain generalization and the learning of cross-domain user behaviour from data. We compare TUS with the state-of-the-art using automatic as well as human evaluations. TUS can compete with rule-based user simulators on pre-defined domains and is able to generalize to unseen domains in a zero-shot fashion.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2021-domain">
<titleInfo>
<title>Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hsien-chin</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nurul</namePart>
<namePart type="family">Lubis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songbo</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carel</namePart>
<namePart type="family">van Niekerk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Geishauser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Heck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shutong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Gasic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gina-Anne</namePart>
<namePart type="family">Levow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitralekha</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many set-ups therefore rely on a user simulator instead of humans. These user simulators have their own problems. While hand-coded, rule-based user simulators have been shown to be sufficient in small, simple domains, for complex domains the number of rules quickly becomes intractable. State-of-the-art data-driven user simulators, on the other hand, are still domain-dependent. This means that adaptation to each new domain requires redesigning and retraining. In this work, we propose a domain-independent transformer-based user simulator (TUS). The structure of TUS is not tied to a specific domain, enabling domain generalization and the learning of cross-domain user behaviour from data. We compare TUS with the state-of-the-art using automatic as well as human evaluations. TUS can compete with rule-based user simulators on pre-defined domains and is able to generalize to unseen domains in a zero-shot fashion.</abstract>
<identifier type="citekey">lin-etal-2021-domain</identifier>
<identifier type="doi">10.18653/v1/2021.sigdial-1.47</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.47</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>445</start>
<end>456</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems
%A Lin, Hsien-chin
%A Lubis, Nurul
%A Hu, Songbo
%A van Niekerk, Carel
%A Geishauser, Christian
%A Heck, Michael
%A Feng, Shutong
%A Gasic, Milica
%Y Li, Haizhou
%Y Levow, Gina-Anne
%Y Yu, Zhou
%Y Gupta, Chitralekha
%Y Sisman, Berrak
%Y Cai, Siqi
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Wu, Yan
%Y Li, Junyi Jessy
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 July
%I Association for Computational Linguistics
%C Singapore and Online
%F lin-etal-2021-domain
%X Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many set-ups therefore rely on a user simulator instead of humans. These user simulators have their own problems. While hand-coded, rule-based user simulators have been shown to be sufficient in small, simple domains, for complex domains the number of rules quickly becomes intractable. State-of-the-art data-driven user simulators, on the other hand, are still domain-dependent. This means that adaptation to each new domain requires redesigning and retraining. In this work, we propose a domain-independent transformer-based user simulator (TUS). The structure of TUS is not tied to a specific domain, enabling domain generalization and the learning of cross-domain user behaviour from data. We compare TUS with the state-of-the-art using automatic as well as human evaluations. TUS can compete with rule-based user simulators on pre-defined domains and is able to generalize to unseen domains in a zero-shot fashion.
%R 10.18653/v1/2021.sigdial-1.47
%U https://aclanthology.org/2021.sigdial-1.47
%U https://doi.org/10.18653/v1/2021.sigdial-1.47
%P 445-456
Markdown (Informal)
[Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems](https://aclanthology.org/2021.sigdial-1.47) (Lin et al., SIGDIAL 2021)
ACL