@inproceedings{daniel-etal-2019-towards,
title = "Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting",
author = "Daniel, Jeanne E. and
Brink, Willie and
Eloff, Ryan and
Copley, Charles",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1090",
doi = "10.18653/v1/P19-1090",
pages = "948--953",
abstract = "We discuss ongoing work into automating a multilingual digital helpdesk service available via text messaging to pregnant and breastfeeding mothers in South Africa. Our anonymized dataset consists of short informal questions, often in low-resource languages, with unreliable language labels, spelling errors and code-mixing, as well as template answers with some inconsistencies. We explore cross-lingual word embeddings, and train parametric and non-parametric models on 90K samples for answer selection from a set of 126 templates. Preliminary results indicate that LSTMs trained end-to-end perform best, with a test accuracy of 62.13{\%} and a recall@5 of 89.56{\%}, and demonstrate that we can accelerate response time by several orders of magnitude.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="daniel-etal-2019-towards">
<titleInfo>
<title>Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeanne</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Daniel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Willie</namePart>
<namePart type="family">Brink</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Eloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Copley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We discuss ongoing work into automating a multilingual digital helpdesk service available via text messaging to pregnant and breastfeeding mothers in South Africa. Our anonymized dataset consists of short informal questions, often in low-resource languages, with unreliable language labels, spelling errors and code-mixing, as well as template answers with some inconsistencies. We explore cross-lingual word embeddings, and train parametric and non-parametric models on 90K samples for answer selection from a set of 126 templates. Preliminary results indicate that LSTMs trained end-to-end perform best, with a test accuracy of 62.13% and a recall@5 of 89.56%, and demonstrate that we can accelerate response time by several orders of magnitude.</abstract>
<identifier type="citekey">daniel-etal-2019-towards</identifier>
<identifier type="doi">10.18653/v1/P19-1090</identifier>
<location>
<url>https://aclanthology.org/P19-1090</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>948</start>
<end>953</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting
%A Daniel, Jeanne E.
%A Brink, Willie
%A Eloff, Ryan
%A Copley, Charles
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F daniel-etal-2019-towards
%X We discuss ongoing work into automating a multilingual digital helpdesk service available via text messaging to pregnant and breastfeeding mothers in South Africa. Our anonymized dataset consists of short informal questions, often in low-resource languages, with unreliable language labels, spelling errors and code-mixing, as well as template answers with some inconsistencies. We explore cross-lingual word embeddings, and train parametric and non-parametric models on 90K samples for answer selection from a set of 126 templates. Preliminary results indicate that LSTMs trained end-to-end perform best, with a test accuracy of 62.13% and a recall@5 of 89.56%, and demonstrate that we can accelerate response time by several orders of magnitude.
%R 10.18653/v1/P19-1090
%U https://aclanthology.org/P19-1090
%U https://doi.org/10.18653/v1/P19-1090
%P 948-953
Markdown (Informal)
[Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting](https://aclanthology.org/P19-1090) (Daniel et al., ACL 2019)
ACL