@inproceedings{boyanov-etal-2017-building,
title = "Building Chatbots from Forum Data: Model Selection Using Question Answering Metrics",
author = "Boyanov, Martin and
Nakov, Preslav and
Moschitti, Alessandro and
Da San Martino, Giovanni and
Koychev, Ivan",
booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-049-6_018",
doi = "10.26615/978-954-452-049-6_018",
pages = "121--129",
abstract = "We propose to use question answering (QA) data from Web forums to train chat-bots from scratch, i.e., without dialog data. First, we extract pairs of question and answer sentences from the typically much longer texts of questions and answers in a forum. We then use these shorter texts to train seq2seq models in a more efficient way. We further improve the parameter optimization using a new model selection strategy based on QA measures. Finally, we propose to use extrinsic evaluation with respect to a QA task as an automatic evaluation method for chatbot systems. The evaluation shows that the model achieves a MAP of 63.5{\%} on the extrinsic task. Moreover, our manual evaluation demonstrates that the model can answer correctly 49.5{\%} of the questions when they are similar in style to how questions are asked in the forum, and 47.3{\%} of the questions, when they are more conversational in style.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boyanov-etal-2017-building">
<titleInfo>
<title>Building Chatbots from Forum Data: Model Selection Using Question Answering Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Boyanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Moschitti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Koychev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-sep</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
</titleInfo>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose to use question answering (QA) data from Web forums to train chat-bots from scratch, i.e., without dialog data. First, we extract pairs of question and answer sentences from the typically much longer texts of questions and answers in a forum. We then use these shorter texts to train seq2seq models in a more efficient way. We further improve the parameter optimization using a new model selection strategy based on QA measures. Finally, we propose to use extrinsic evaluation with respect to a QA task as an automatic evaluation method for chatbot systems. The evaluation shows that the model achieves a MAP of 63.5% on the extrinsic task. Moreover, our manual evaluation demonstrates that the model can answer correctly 49.5% of the questions when they are similar in style to how questions are asked in the forum, and 47.3% of the questions, when they are more conversational in style.</abstract>
<identifier type="citekey">boyanov-etal-2017-building</identifier>
<identifier type="doi">10.26615/978-954-452-049-6_018</identifier>
<part>
<date>2017-sep</date>
<extent unit="page">
<start>121</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Chatbots from Forum Data: Model Selection Using Question Answering Metrics
%A Boyanov, Martin
%A Nakov, Preslav
%A Moschitti, Alessandro
%A Da San Martino, Giovanni
%A Koychev, Ivan
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 sep
%I INCOMA Ltd.
%C Varna, Bulgaria
%F boyanov-etal-2017-building
%X We propose to use question answering (QA) data from Web forums to train chat-bots from scratch, i.e., without dialog data. First, we extract pairs of question and answer sentences from the typically much longer texts of questions and answers in a forum. We then use these shorter texts to train seq2seq models in a more efficient way. We further improve the parameter optimization using a new model selection strategy based on QA measures. Finally, we propose to use extrinsic evaluation with respect to a QA task as an automatic evaluation method for chatbot systems. The evaluation shows that the model achieves a MAP of 63.5% on the extrinsic task. Moreover, our manual evaluation demonstrates that the model can answer correctly 49.5% of the questions when they are similar in style to how questions are asked in the forum, and 47.3% of the questions, when they are more conversational in style.
%R 10.26615/978-954-452-049-6_018
%U https://doi.org/10.26615/978-954-452-049-6_018
%P 121-129
Markdown (Informal)
[Building Chatbots from Forum Data: Model Selection Using Question Answering Metrics](https://doi.org/10.26615/978-954-452-049-6_018) (Boyanov et al., RANLP 2017)
ACL