@inproceedings{dernoncourt-lee-2017-pubmed,
title = "{P}ub{M}ed 200k {RCT}: a Dataset for Sequential Sentence Classification in Medical Abstracts",
author = "Dernoncourt, Franck and
Lee, Ji Young",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-2052",
pages = "308--313",
abstract = "We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3 million sentences. Each sentence of each abstract is labeled with their role in the abstract using one of the following classes: background, objective, method, result, or conclusion. The purpose of releasing this dataset is twofold. First, the majority of datasets for sequential short-text classification (i.e., classification of short texts that appear in sequences) are small: we hope that releasing a new large dataset will help develop more accurate algorithms for this task. Second, from an application perspective, researchers need better tools to efficiently skim through the literature. Automatically classifying each sentence in an abstract would help researchers read abstracts more efficiently, especially in fields where abstracts may be long, such as the medical field.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dernoncourt-lee-2017-pubmed">
<titleInfo>
<title>PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="given">Young</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3 million sentences. Each sentence of each abstract is labeled with their role in the abstract using one of the following classes: background, objective, method, result, or conclusion. The purpose of releasing this dataset is twofold. First, the majority of datasets for sequential short-text classification (i.e., classification of short texts that appear in sequences) are small: we hope that releasing a new large dataset will help develop more accurate algorithms for this task. Second, from an application perspective, researchers need better tools to efficiently skim through the literature. Automatically classifying each sentence in an abstract would help researchers read abstracts more efficiently, especially in fields where abstracts may be long, such as the medical field.</abstract>
<identifier type="citekey">dernoncourt-lee-2017-pubmed</identifier>
<location>
<url>https://aclanthology.org/I17-2052</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>308</start>
<end>313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts
%A Dernoncourt, Franck
%A Lee, Ji Young
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F dernoncourt-lee-2017-pubmed
%X We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3 million sentences. Each sentence of each abstract is labeled with their role in the abstract using one of the following classes: background, objective, method, result, or conclusion. The purpose of releasing this dataset is twofold. First, the majority of datasets for sequential short-text classification (i.e., classification of short texts that appear in sequences) are small: we hope that releasing a new large dataset will help develop more accurate algorithms for this task. Second, from an application perspective, researchers need better tools to efficiently skim through the literature. Automatically classifying each sentence in an abstract would help researchers read abstracts more efficiently, especially in fields where abstracts may be long, such as the medical field.
%U https://aclanthology.org/I17-2052
%P 308-313
Markdown (Informal)
[PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts](https://aclanthology.org/I17-2052) (Dernoncourt & Lee, IJCNLP 2017)
ACL