@inproceedings{jhunjhunwala-etal-2020-multi,
title = "Multi-Action Dialog Policy Learning with Interactive Human Teaching",
author = "Jhunjhunwala, Megha and
Bryant, Caleb and
Shah, Pararth",
editor = "Pietquin, Olivier and
Muresan, Smaranda and
Chen, Vivian and
Kennington, Casey and
Vandyke, David and
Dethlefs, Nina and
Inoue, Koji and
Ekstedt, Erik and
Ultes, Stefan",
booktitle = "Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2020",
address = "1st virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sigdial-1.36",
doi = "10.18653/v1/2020.sigdial-1.36",
pages = "290--296",
abstract = "We present a framework for improving task-oriented dialog systems through online interactive teaching with human trainers. A dialog policy trained with imitation learning on a limited corpus may not generalize well to novel dialog flows often uncovered in live interactions. This issue is magnified in multi-action dialog policies which have a more expressive action space. In our approach, a pre-trained dialog policy model interacts with human trainers, and at each turn the trainers choose the best output among N-best multi-action outputs. We present a novel multi-domain, multi-action dialog policy architecture trained on MultiWOZ, and show that small amounts of online supervision can lead to significant improvement in model performance. We also present transfer learning results which show that interactive learning in one domain improves policy model performance in related domains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jhunjhunwala-etal-2020-multi">
<titleInfo>
<title>Multi-Action Dialog Policy Learning with Interactive Human Teaching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Megha</namePart>
<namePart type="family">Jhunjhunwala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caleb</namePart>
<namePart type="family">Bryant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pararth</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Pietquin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Chen</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">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">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Ekstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">1st virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a framework for improving task-oriented dialog systems through online interactive teaching with human trainers. A dialog policy trained with imitation learning on a limited corpus may not generalize well to novel dialog flows often uncovered in live interactions. This issue is magnified in multi-action dialog policies which have a more expressive action space. In our approach, a pre-trained dialog policy model interacts with human trainers, and at each turn the trainers choose the best output among N-best multi-action outputs. We present a novel multi-domain, multi-action dialog policy architecture trained on MultiWOZ, and show that small amounts of online supervision can lead to significant improvement in model performance. We also present transfer learning results which show that interactive learning in one domain improves policy model performance in related domains.</abstract>
<identifier type="citekey">jhunjhunwala-etal-2020-multi</identifier>
<identifier type="doi">10.18653/v1/2020.sigdial-1.36</identifier>
<location>
<url>https://aclanthology.org/2020.sigdial-1.36</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>290</start>
<end>296</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Action Dialog Policy Learning with Interactive Human Teaching
%A Jhunjhunwala, Megha
%A Bryant, Caleb
%A Shah, Pararth
%Y Pietquin, Olivier
%Y Muresan, Smaranda
%Y Chen, Vivian
%Y Kennington, Casey
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Inoue, Koji
%Y Ekstedt, Erik
%Y Ultes, Stefan
%S Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2020
%8 July
%I Association for Computational Linguistics
%C 1st virtual meeting
%F jhunjhunwala-etal-2020-multi
%X We present a framework for improving task-oriented dialog systems through online interactive teaching with human trainers. A dialog policy trained with imitation learning on a limited corpus may not generalize well to novel dialog flows often uncovered in live interactions. This issue is magnified in multi-action dialog policies which have a more expressive action space. In our approach, a pre-trained dialog policy model interacts with human trainers, and at each turn the trainers choose the best output among N-best multi-action outputs. We present a novel multi-domain, multi-action dialog policy architecture trained on MultiWOZ, and show that small amounts of online supervision can lead to significant improvement in model performance. We also present transfer learning results which show that interactive learning in one domain improves policy model performance in related domains.
%R 10.18653/v1/2020.sigdial-1.36
%U https://aclanthology.org/2020.sigdial-1.36
%U https://doi.org/10.18653/v1/2020.sigdial-1.36
%P 290-296
Markdown (Informal)
[Multi-Action Dialog Policy Learning with Interactive Human Teaching](https://aclanthology.org/2020.sigdial-1.36) (Jhunjhunwala et al., SIGDIAL 2020)
ACL