@inproceedings{papangelis-etal-2021-generative,
title = "Generative Conversational Networks",
author = "Papangelis, Alexandros and
Gopalakrishnan, Karthik and
Padmakumar, Aishwarya and
Kim, Seokhwan and
Tur, Gokhan and
Hakkani-Tur, Dilek",
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-1.12",
doi = "10.18653/v1/2021.sigdial-1.12",
pages = "111--120",
abstract = "Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent{'}s performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35{\%} in intent detection and 21{\%} in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papangelis-etal-2021-generative">
<titleInfo>
<title>Generative Conversational Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Gopalakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokhan</namePart>
<namePart type="family">Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</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>Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent’s performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.</abstract>
<identifier type="citekey">papangelis-etal-2021-generative</identifier>
<identifier type="doi">10.18653/v1/2021.sigdial-1.12</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.12</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>111</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generative Conversational Networks
%A Papangelis, Alexandros
%A Gopalakrishnan, Karthik
%A Padmakumar, Aishwarya
%A Kim, Seokhwan
%A Tur, Gokhan
%A Hakkani-Tur, Dilek
%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 papangelis-etal-2021-generative
%X Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent’s performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.
%R 10.18653/v1/2021.sigdial-1.12
%U https://aclanthology.org/2021.sigdial-1.12
%U https://doi.org/10.18653/v1/2021.sigdial-1.12
%P 111-120
Markdown (Informal)
[Generative Conversational Networks](https://aclanthology.org/2021.sigdial-1.12) (Papangelis et al., SIGDIAL 2021)
ACL
- Alexandros Papangelis, Karthik Gopalakrishnan, Aishwarya Padmakumar, Seokhwan Kim, Gokhan Tur, and Dilek Hakkani-Tur. 2021. Generative Conversational Networks. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 111–120, Singapore and Online. Association for Computational Linguistics.