@inproceedings{faessler-etal-2020-progene,
title = "{P}ro{G}ene - A Large-scale, High-Quality Protein-Gene Annotated Benchmark Corpus",
author = "Faessler, Erik and
Modersohn, Luise and
Lohr, Christina and
Hahn, Udo",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.564",
pages = "4585--4596",
abstract = "Genes and proteins constitute the fundamental entities of molecular genetics. We here introduce ProGene (formerly called FSU-PRGE), a corpus that reflects our efforts to cope with this important class of named entities within the framework of a long-lasting large-scale annotation campaign at the Jena University Language {\&} Information Engineering (JULIE) Lab. We assembled the entire corpus from 11 subcorpora covering various biological domains to achieve an overall subdomain-independent corpus. It consists of 3,308 MEDLINE abstracts with over 36k sentences and more than 960k tokens annotated with nearly 60k named entity mentions. Two annotators strove for carefully assigning entity mentions to classes of genes/proteins as well as families/groups, complexes, variants and enumerations of those where genes and proteins are represented by a single class. The main purpose of the corpus is to provide a large body of consistent and reliable annotations for supervised training and evaluation of machine learning algorithms in this relevant domain. Furthermore, we provide an evaluation of two state-of-the-art baseline systems {---} BioBert and flair {---} on the ProGene corpus. We make the evaluation datasets and the trained models available to encourage comparable evaluations of new methods in the future.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faessler-etal-2020-progene">
<titleInfo>
<title>ProGene - A Large-scale, High-Quality Protein-Gene Annotated Benchmark Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Faessler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luise</namePart>
<namePart type="family">Modersohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Lohr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Genes and proteins constitute the fundamental entities of molecular genetics. We here introduce ProGene (formerly called FSU-PRGE), a corpus that reflects our efforts to cope with this important class of named entities within the framework of a long-lasting large-scale annotation campaign at the Jena University Language & Information Engineering (JULIE) Lab. We assembled the entire corpus from 11 subcorpora covering various biological domains to achieve an overall subdomain-independent corpus. It consists of 3,308 MEDLINE abstracts with over 36k sentences and more than 960k tokens annotated with nearly 60k named entity mentions. Two annotators strove for carefully assigning entity mentions to classes of genes/proteins as well as families/groups, complexes, variants and enumerations of those where genes and proteins are represented by a single class. The main purpose of the corpus is to provide a large body of consistent and reliable annotations for supervised training and evaluation of machine learning algorithms in this relevant domain. Furthermore, we provide an evaluation of two state-of-the-art baseline systems — BioBert and flair — on the ProGene corpus. We make the evaluation datasets and the trained models available to encourage comparable evaluations of new methods in the future.</abstract>
<identifier type="citekey">faessler-etal-2020-progene</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.564</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4585</start>
<end>4596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ProGene - A Large-scale, High-Quality Protein-Gene Annotated Benchmark Corpus
%A Faessler, Erik
%A Modersohn, Luise
%A Lohr, Christina
%A Hahn, Udo
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F faessler-etal-2020-progene
%X Genes and proteins constitute the fundamental entities of molecular genetics. We here introduce ProGene (formerly called FSU-PRGE), a corpus that reflects our efforts to cope with this important class of named entities within the framework of a long-lasting large-scale annotation campaign at the Jena University Language & Information Engineering (JULIE) Lab. We assembled the entire corpus from 11 subcorpora covering various biological domains to achieve an overall subdomain-independent corpus. It consists of 3,308 MEDLINE abstracts with over 36k sentences and more than 960k tokens annotated with nearly 60k named entity mentions. Two annotators strove for carefully assigning entity mentions to classes of genes/proteins as well as families/groups, complexes, variants and enumerations of those where genes and proteins are represented by a single class. The main purpose of the corpus is to provide a large body of consistent and reliable annotations for supervised training and evaluation of machine learning algorithms in this relevant domain. Furthermore, we provide an evaluation of two state-of-the-art baseline systems — BioBert and flair — on the ProGene corpus. We make the evaluation datasets and the trained models available to encourage comparable evaluations of new methods in the future.
%U https://aclanthology.org/2020.lrec-1.564
%P 4585-4596
Markdown (Informal)
[ProGene - A Large-scale, High-Quality Protein-Gene Annotated Benchmark Corpus](https://aclanthology.org/2020.lrec-1.564) (Faessler et al., LREC 2020)
ACL