@inproceedings{eric-2017-document,
title = "Document retrieval and question answering in medical documents. A large-scale corpus challenge.",
author = "Eric, Curea",
editor = "Boytcheva, Svetla and
Cohen, Kevin Bretonnel and
Savova, Guergana and
Angelova, Galia",
booktitle = "Proceedings of the Biomedical {NLP} Workshop associated with {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-044-1_001",
doi = "10.26615/978-954-452-044-1_001",
pages = "1--7",
abstract = "Whenever employed on large datasets, information retrieval works by isolating a subset of documents from the larger dataset and then proceeding with low-level processing of the text. This is usually carried out by means of adding index-terms to each document in the collection. In this paper we deal with automatic document classification and index-term detection applied on large-scale medical corpora. In our methodology we employ a linear classifier and we test our results on the BioASQ training corpora, which is a collection of 12 million MeSH-indexed medical abstracts. We cover both term-indexing, result retrieval and result ranking based on distributed word representations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eric-2017-document">
<titleInfo>
<title>Document retrieval and question answering in medical documents. A large-scale corpus challenge.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Curea</namePart>
<namePart type="family">Eric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Biomedical NLP Workshop associated with RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetla</namePart>
<namePart type="family">Boytcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guergana</namePart>
<namePart type="family">Savova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Whenever employed on large datasets, information retrieval works by isolating a subset of documents from the larger dataset and then proceeding with low-level processing of the text. This is usually carried out by means of adding index-terms to each document in the collection. In this paper we deal with automatic document classification and index-term detection applied on large-scale medical corpora. In our methodology we employ a linear classifier and we test our results on the BioASQ training corpora, which is a collection of 12 million MeSH-indexed medical abstracts. We cover both term-indexing, result retrieval and result ranking based on distributed word representations.</abstract>
<identifier type="citekey">eric-2017-document</identifier>
<identifier type="doi">10.26615/978-954-452-044-1_001</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>1</start>
<end>7</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document retrieval and question answering in medical documents. A large-scale corpus challenge.
%A Eric, Curea
%Y Boytcheva, Svetla
%Y Cohen, Kevin Bretonnel
%Y Savova, Guergana
%Y Angelova, Galia
%S Proceedings of the Biomedical NLP Workshop associated with RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F eric-2017-document
%X Whenever employed on large datasets, information retrieval works by isolating a subset of documents from the larger dataset and then proceeding with low-level processing of the text. This is usually carried out by means of adding index-terms to each document in the collection. In this paper we deal with automatic document classification and index-term detection applied on large-scale medical corpora. In our methodology we employ a linear classifier and we test our results on the BioASQ training corpora, which is a collection of 12 million MeSH-indexed medical abstracts. We cover both term-indexing, result retrieval and result ranking based on distributed word representations.
%R 10.26615/978-954-452-044-1_001
%U https://doi.org/10.26615/978-954-452-044-1_001
%P 1-7
Markdown (Informal)
[Document retrieval and question answering in medical documents. A large-scale corpus challenge.](https://doi.org/10.26615/978-954-452-044-1_001) (Eric, RANLP 2017)
ACL