@inproceedings{herrmannova-etal-2018-unsupervised,
title = "Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study",
author = "Herrmannova, Drahomira and
Young, Steven and
Patton, Robert and
Stahl, Christopher and
Kleinstreuer, Nicole and
Wolfe, Mary",
editor = "Lavelli, Alberto and
Minard, Anne-Lyse and
Rinaldi, Fabio",
booktitle = "Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5609/",
doi = "10.18653/v1/W18-5609",
pages = "71--82",
abstract = "Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements in an unsupervised manner. Specifically, provided a set of criteria describing specific study parameters, such as species, route of administration, and dosing regimen, we develop an unsupervised approach to identify text segments (sentences) relevant to the criteria. A binary classifier trained to identify publications that met the criteria performs better when trained on the candidate sentences than when trained on sentences randomly picked from the text, supporting the intuition that our method is able to accurately identify study descriptors."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="herrmannova-etal-2018-unsupervised">
<titleInfo>
<title>Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Drahomira</namePart>
<namePart type="family">Herrmannova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Young</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Patton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Stahl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicole</namePart>
<namePart type="family">Kleinstreuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Wolfe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements in an unsupervised manner. Specifically, provided a set of criteria describing specific study parameters, such as species, route of administration, and dosing regimen, we develop an unsupervised approach to identify text segments (sentences) relevant to the criteria. A binary classifier trained to identify publications that met the criteria performs better when trained on the candidate sentences than when trained on sentences randomly picked from the text, supporting the intuition that our method is able to accurately identify study descriptors.</abstract>
<identifier type="citekey">herrmannova-etal-2018-unsupervised</identifier>
<identifier type="doi">10.18653/v1/W18-5609</identifier>
<location>
<url>https://aclanthology.org/W18-5609/</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>71</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study
%A Herrmannova, Drahomira
%A Young, Steven
%A Patton, Robert
%A Stahl, Christopher
%A Kleinstreuer, Nicole
%A Wolfe, Mary
%Y Lavelli, Alberto
%Y Minard, Anne-Lyse
%Y Rinaldi, Fabio
%S Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F herrmannova-etal-2018-unsupervised
%X Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements in an unsupervised manner. Specifically, provided a set of criteria describing specific study parameters, such as species, route of administration, and dosing regimen, we develop an unsupervised approach to identify text segments (sentences) relevant to the criteria. A binary classifier trained to identify publications that met the criteria performs better when trained on the candidate sentences than when trained on sentences randomly picked from the text, supporting the intuition that our method is able to accurately identify study descriptors.
%R 10.18653/v1/W18-5609
%U https://aclanthology.org/W18-5609/
%U https://doi.org/10.18653/v1/W18-5609
%P 71-82
Markdown (Informal)
[Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study](https://aclanthology.org/W18-5609/) (Herrmannova et al., Louhi 2018)
ACL