@inproceedings{poddar-etal-2022-deploying,
title = "Deploying a Retrieval based Response Model for Task Oriented Dialogues",
author = {Poddar, Lahari and
Szarvas, Gy{\"o}rgy and
Wang, Cheng and
Balazs, Jorge and
Danchenko, Pavel and
Ernst, Patrick},
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.17",
doi = "10.18653/v1/2022.emnlp-industry.17",
pages = "169--178",
abstract = "Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a conversational model that satisfies these criteria and can efficiently scale to rank a large set of response candidates. First, we provide a simple algorithm to semi-automatically create a high-coverage template set from historic conversations without any annotation. Second, we propose a neural architecture that encodes the dialogue context and applicable business constraints as profile features for ranking the next turn. Third, we describe a two-stage learning strategy with self-supervised training, followed by supervised fine-tuning on limited data collected through a human-in-the-loop platform. Finally, we describe offline experiments and present results of deploying our model with human-in-the-loop to converse with live customers online.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poddar-etal-2022-deploying">
<titleInfo>
<title>Deploying a Retrieval based Response Model for Task Oriented Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lahari</namePart>
<namePart type="family">Poddar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Szarvas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Balazs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Danchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Ernst</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a conversational model that satisfies these criteria and can efficiently scale to rank a large set of response candidates. First, we provide a simple algorithm to semi-automatically create a high-coverage template set from historic conversations without any annotation. Second, we propose a neural architecture that encodes the dialogue context and applicable business constraints as profile features for ranking the next turn. Third, we describe a two-stage learning strategy with self-supervised training, followed by supervised fine-tuning on limited data collected through a human-in-the-loop platform. Finally, we describe offline experiments and present results of deploying our model with human-in-the-loop to converse with live customers online.</abstract>
<identifier type="citekey">poddar-etal-2022-deploying</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.17</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.17</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>169</start>
<end>178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deploying a Retrieval based Response Model for Task Oriented Dialogues
%A Poddar, Lahari
%A Szarvas, György
%A Wang, Cheng
%A Balazs, Jorge
%A Danchenko, Pavel
%A Ernst, Patrick
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F poddar-etal-2022-deploying
%X Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a conversational model that satisfies these criteria and can efficiently scale to rank a large set of response candidates. First, we provide a simple algorithm to semi-automatically create a high-coverage template set from historic conversations without any annotation. Second, we propose a neural architecture that encodes the dialogue context and applicable business constraints as profile features for ranking the next turn. Third, we describe a two-stage learning strategy with self-supervised training, followed by supervised fine-tuning on limited data collected through a human-in-the-loop platform. Finally, we describe offline experiments and present results of deploying our model with human-in-the-loop to converse with live customers online.
%R 10.18653/v1/2022.emnlp-industry.17
%U https://aclanthology.org/2022.emnlp-industry.17
%U https://doi.org/10.18653/v1/2022.emnlp-industry.17
%P 169-178
Markdown (Informal)
[Deploying a Retrieval based Response Model for Task Oriented Dialogues](https://aclanthology.org/2022.emnlp-industry.17) (Poddar et al., EMNLP 2022)
ACL
- Lahari Poddar, György Szarvas, Cheng Wang, Jorge Balazs, Pavel Danchenko, and Patrick Ernst. 2022. Deploying a Retrieval based Response Model for Task Oriented Dialogues. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 169–178, Abu Dhabi, UAE. Association for Computational Linguistics.