@inproceedings{liednikova-etal-2020-learning,
title = "Learning Health-Bots from Training Data that was Automatically Created using Paraphrase Detection and Expert Knowledge",
author = "Liednikova, Anna and
Jolivet, Philippe and
Durand-Salmon, Alexandre and
Gardent, Claire",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.55",
doi = "10.18653/v1/2020.coling-main.55",
pages = "638--648",
abstract = "A key bottleneck for developing dialog models is the lack of adequate training data. Due to privacy issues, dialog data is even scarcer in the health domain. We propose a novel method for creating dialog corpora which we apply to create doctor-patient interaction data. We use this data to learn both a generation and a hybrid classification/retrieval model and find that the generation model consistently outperforms the hybrid model. We show that our data creation method has several advantages. Not only does it allow for the semi-automatic creation of large quantities of training data. It also provides a natural way of guiding learning and a novel method for assessing the quality of human-machine interactions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liednikova-etal-2020-learning">
<titleInfo>
<title>Learning Health-Bots from Training Data that was Automatically Created using Paraphrase Detection and Expert Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Liednikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Jolivet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Durand-Salmon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Gardent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A key bottleneck for developing dialog models is the lack of adequate training data. Due to privacy issues, dialog data is even scarcer in the health domain. We propose a novel method for creating dialog corpora which we apply to create doctor-patient interaction data. We use this data to learn both a generation and a hybrid classification/retrieval model and find that the generation model consistently outperforms the hybrid model. We show that our data creation method has several advantages. Not only does it allow for the semi-automatic creation of large quantities of training data. It also provides a natural way of guiding learning and a novel method for assessing the quality of human-machine interactions.</abstract>
<identifier type="citekey">liednikova-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.55</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.55</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>638</start>
<end>648</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Health-Bots from Training Data that was Automatically Created using Paraphrase Detection and Expert Knowledge
%A Liednikova, Anna
%A Jolivet, Philippe
%A Durand-Salmon, Alexandre
%A Gardent, Claire
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 dec
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F liednikova-etal-2020-learning
%X A key bottleneck for developing dialog models is the lack of adequate training data. Due to privacy issues, dialog data is even scarcer in the health domain. We propose a novel method for creating dialog corpora which we apply to create doctor-patient interaction data. We use this data to learn both a generation and a hybrid classification/retrieval model and find that the generation model consistently outperforms the hybrid model. We show that our data creation method has several advantages. Not only does it allow for the semi-automatic creation of large quantities of training data. It also provides a natural way of guiding learning and a novel method for assessing the quality of human-machine interactions.
%R 10.18653/v1/2020.coling-main.55
%U https://aclanthology.org/2020.coling-main.55
%U https://doi.org/10.18653/v1/2020.coling-main.55
%P 638-648
Markdown (Informal)
[Learning Health-Bots from Training Data that was Automatically Created using Paraphrase Detection and Expert Knowledge](https://aclanthology.org/2020.coling-main.55) (Liednikova et al., COLING 2020)
ACL