@inproceedings{bodirlau-etal-2019-cross,
title = "Cross-Domain Training for Goal-Oriented Conversational Agents",
author = "Bod{\^\i}rl{\u{a}}u, Alexandra Maria and
Budulan, Stefania and
Rebedea, Traian",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R19-1017",
doi = "10.26615/978-954-452-056-4_017",
pages = "142--150",
abstract = "Goal-Oriented Chatbots in fields such as customer support, providing certain information or general help with bookings or reservations, suffer from low performance partly due to the difficulty of obtaining large domain-specific annotated datasets. Given that the problem is closely related to the domain of the conversational agent and the data belonging to a specific domain is difficult to annotate, there have been some attempts at surpassing these challenges such as unsupervised pre-training or transfer learning between different domains. A more thorough analysis of the transfer learning mechanism is justified by the significant improvement of the results demonstrated in the results section. We describe extensive experiments using transfer learning and warm-starting techniques with improvements of more than 5{\%} in relative percentage of success rate in the majority of cases, and up to 10x faster convergence as opposed to training the system without them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bodirlau-etal-2019-cross">
<titleInfo>
<title>Cross-Domain Training for Goal-Oriented Conversational Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Bodîrlău</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Budulan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Traian</namePart>
<namePart type="family">Rebedea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-sep</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</title>
</titleInfo>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Goal-Oriented Chatbots in fields such as customer support, providing certain information or general help with bookings or reservations, suffer from low performance partly due to the difficulty of obtaining large domain-specific annotated datasets. Given that the problem is closely related to the domain of the conversational agent and the data belonging to a specific domain is difficult to annotate, there have been some attempts at surpassing these challenges such as unsupervised pre-training or transfer learning between different domains. A more thorough analysis of the transfer learning mechanism is justified by the significant improvement of the results demonstrated in the results section. We describe extensive experiments using transfer learning and warm-starting techniques with improvements of more than 5% in relative percentage of success rate in the majority of cases, and up to 10x faster convergence as opposed to training the system without them.</abstract>
<identifier type="citekey">bodirlau-etal-2019-cross</identifier>
<identifier type="doi">10.26615/978-954-452-056-4_017</identifier>
<location>
<url>https://aclanthology.org/R19-1017</url>
</location>
<part>
<date>2019-sep</date>
<extent unit="page">
<start>142</start>
<end>150</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Domain Training for Goal-Oriented Conversational Agents
%A Bodîrlău, Alexandra Maria
%A Budulan, Stefania
%A Rebedea, Traian
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 sep
%I INCOMA Ltd.
%C Varna, Bulgaria
%F bodirlau-etal-2019-cross
%X Goal-Oriented Chatbots in fields such as customer support, providing certain information or general help with bookings or reservations, suffer from low performance partly due to the difficulty of obtaining large domain-specific annotated datasets. Given that the problem is closely related to the domain of the conversational agent and the data belonging to a specific domain is difficult to annotate, there have been some attempts at surpassing these challenges such as unsupervised pre-training or transfer learning between different domains. A more thorough analysis of the transfer learning mechanism is justified by the significant improvement of the results demonstrated in the results section. We describe extensive experiments using transfer learning and warm-starting techniques with improvements of more than 5% in relative percentage of success rate in the majority of cases, and up to 10x faster convergence as opposed to training the system without them.
%R 10.26615/978-954-452-056-4_017
%U https://aclanthology.org/R19-1017
%U https://doi.org/10.26615/978-954-452-056-4_017
%P 142-150
Markdown (Informal)
[Cross-Domain Training for Goal-Oriented Conversational Agents](https://aclanthology.org/R19-1017) (Bodîrlău et al., RANLP 2019)
ACL