@inproceedings{wu-rasmussen-2021-clipping,
title = "Clipping Loops for Sample-Efficient Dialogue Policy Optimisation",
author = "Wu, Yen-Chen and
Rasmussen, Carl Edward",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.267",
doi = "10.18653/v1/2021.naacl-main.267",
pages = "3420--3428",
abstract = "Training dialogue agents requires a large number of interactions with users: agents have no idea about which responses are bad among a lengthy dialogue. In this paper, we propose loop-clipping policy optimisation (LCPO) to eliminate useless responses. LCPO consists of two stages: loop clipping and advantage clipping. In loop clipping, we clip off useless responses (called loops) from dialogue history (called trajectories). The clipped trajectories are more succinct than the original ones, and the estimation of state-value is more accurate. Second, in advantage clipping, we estimate and clip the advantages of useless responses and normal ones separately. The clipped advantage distinguish useless actions from others and reduce the probabilities of useless actions efficiently. In experiments on Cambridge Restaurant Dialogue System, LCPO uses only 260 training dialogues to achieve 80{\%} success rate, while PPO baseline requires 2160 dialogues. Besides, LCPO receives 3.7/5 scores in human evaluation where the agent interactively collects 100 real-user dialogues in training phase.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-rasmussen-2021-clipping">
<titleInfo>
<title>Clipping Loops for Sample-Efficient Dialogue Policy Optimisation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yen-Chen</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="given">Edward</namePart>
<namePart type="family">Rasmussen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Training dialogue agents requires a large number of interactions with users: agents have no idea about which responses are bad among a lengthy dialogue. In this paper, we propose loop-clipping policy optimisation (LCPO) to eliminate useless responses. LCPO consists of two stages: loop clipping and advantage clipping. In loop clipping, we clip off useless responses (called loops) from dialogue history (called trajectories). The clipped trajectories are more succinct than the original ones, and the estimation of state-value is more accurate. Second, in advantage clipping, we estimate and clip the advantages of useless responses and normal ones separately. The clipped advantage distinguish useless actions from others and reduce the probabilities of useless actions efficiently. In experiments on Cambridge Restaurant Dialogue System, LCPO uses only 260 training dialogues to achieve 80% success rate, while PPO baseline requires 2160 dialogues. Besides, LCPO receives 3.7/5 scores in human evaluation where the agent interactively collects 100 real-user dialogues in training phase.</abstract>
<identifier type="citekey">wu-rasmussen-2021-clipping</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.267</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.267</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3420</start>
<end>3428</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clipping Loops for Sample-Efficient Dialogue Policy Optimisation
%A Wu, Yen-Chen
%A Rasmussen, Carl Edward
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F wu-rasmussen-2021-clipping
%X Training dialogue agents requires a large number of interactions with users: agents have no idea about which responses are bad among a lengthy dialogue. In this paper, we propose loop-clipping policy optimisation (LCPO) to eliminate useless responses. LCPO consists of two stages: loop clipping and advantage clipping. In loop clipping, we clip off useless responses (called loops) from dialogue history (called trajectories). The clipped trajectories are more succinct than the original ones, and the estimation of state-value is more accurate. Second, in advantage clipping, we estimate and clip the advantages of useless responses and normal ones separately. The clipped advantage distinguish useless actions from others and reduce the probabilities of useless actions efficiently. In experiments on Cambridge Restaurant Dialogue System, LCPO uses only 260 training dialogues to achieve 80% success rate, while PPO baseline requires 2160 dialogues. Besides, LCPO receives 3.7/5 scores in human evaluation where the agent interactively collects 100 real-user dialogues in training phase.
%R 10.18653/v1/2021.naacl-main.267
%U https://aclanthology.org/2021.naacl-main.267
%U https://doi.org/10.18653/v1/2021.naacl-main.267
%P 3420-3428
Markdown (Informal)
[Clipping Loops for Sample-Efficient Dialogue Policy Optimisation](https://aclanthology.org/2021.naacl-main.267) (Wu & Rasmussen, NAACL 2021)
ACL
- Yen-Chen Wu and Carl Edward Rasmussen. 2021. Clipping Loops for Sample-Efficient Dialogue Policy Optimisation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3420–3428, Online. Association for Computational Linguistics.