@inproceedings{el-haj-etal-2020-infrastructure,
title = "Infrastructure for Semantic Annotation in the Genomics Domain",
author = "El-Haj, Mahmoud and
Rutherford, Nathan and
Coole, Matthew and
Ezeani, Ignatius and
Prentice, Sheryl and
Ide, Nancy and
Knight, Jo and
Piao, Scott and
Mariani, John and
Rayson, Paul and
Suderman, Keith",
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-1.855/",
pages = "6921--6929",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "We describe a novel super-infrastructure for biomedical text mining which incorporates an end-to-end pipeline for the collection, annotation, storage, retrieval and analysis of biomedical and life sciences literature, combining NLP and corpus linguistics methods. The infrastructure permits extreme-scale research on the open access PubMed Central archive. It combines an updatable Gene Ontology Semantic Tagger (GOST) for entity identification and semantic markup in the literature, with a NLP pipeline scheduler (Buster) to collect and process the corpus, and a bespoke columnar corpus database (LexiDB) for indexing. The corpus database is distributed to permit fast indexing, and provides a simple web front-end with corpus linguistics methods for sub-corpus comparison and retrieval. GOST is also connected as a service in the Language Application (LAPPS) Grid, in which context it is interoperable with other NLP tools and data in the Grid and can be combined with them in more complex workflows. In a literature based discovery setting, we have created an annotated corpus of 9,776 papers with 5,481,543 words."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-haj-etal-2020-infrastructure">
<titleInfo>
<title>Infrastructure for Semantic Annotation in the Genomics Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Rutherford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Coole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ignatius</namePart>
<namePart type="family">Ezeani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheryl</namePart>
<namePart type="family">Prentice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jo</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Piao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="family">Suderman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">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>We describe a novel super-infrastructure for biomedical text mining which incorporates an end-to-end pipeline for the collection, annotation, storage, retrieval and analysis of biomedical and life sciences literature, combining NLP and corpus linguistics methods. The infrastructure permits extreme-scale research on the open access PubMed Central archive. It combines an updatable Gene Ontology Semantic Tagger (GOST) for entity identification and semantic markup in the literature, with a NLP pipeline scheduler (Buster) to collect and process the corpus, and a bespoke columnar corpus database (LexiDB) for indexing. The corpus database is distributed to permit fast indexing, and provides a simple web front-end with corpus linguistics methods for sub-corpus comparison and retrieval. GOST is also connected as a service in the Language Application (LAPPS) Grid, in which context it is interoperable with other NLP tools and data in the Grid and can be combined with them in more complex workflows. In a literature based discovery setting, we have created an annotated corpus of 9,776 papers with 5,481,543 words.</abstract>
<identifier type="citekey">el-haj-etal-2020-infrastructure</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.855/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6921</start>
<end>6929</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Infrastructure for Semantic Annotation in the Genomics Domain
%A El-Haj, Mahmoud
%A Rutherford, Nathan
%A Coole, Matthew
%A Ezeani, Ignatius
%A Prentice, Sheryl
%A Ide, Nancy
%A Knight, Jo
%A Piao, Scott
%A Mariani, John
%A Rayson, Paul
%A Suderman, Keith
%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 eng
%F el-haj-etal-2020-infrastructure
%X We describe a novel super-infrastructure for biomedical text mining which incorporates an end-to-end pipeline for the collection, annotation, storage, retrieval and analysis of biomedical and life sciences literature, combining NLP and corpus linguistics methods. The infrastructure permits extreme-scale research on the open access PubMed Central archive. It combines an updatable Gene Ontology Semantic Tagger (GOST) for entity identification and semantic markup in the literature, with a NLP pipeline scheduler (Buster) to collect and process the corpus, and a bespoke columnar corpus database (LexiDB) for indexing. The corpus database is distributed to permit fast indexing, and provides a simple web front-end with corpus linguistics methods for sub-corpus comparison and retrieval. GOST is also connected as a service in the Language Application (LAPPS) Grid, in which context it is interoperable with other NLP tools and data in the Grid and can be combined with them in more complex workflows. In a literature based discovery setting, we have created an annotated corpus of 9,776 papers with 5,481,543 words.
%U https://aclanthology.org/2020.lrec-1.855/
%P 6921-6929
Markdown (Informal)
[Infrastructure for Semantic Annotation in the Genomics Domain](https://aclanthology.org/2020.lrec-1.855/) (El-Haj et al., LREC 2020)
ACL
- Mahmoud El-Haj, Nathan Rutherford, Matthew Coole, Ignatius Ezeani, Sheryl Prentice, Nancy Ide, Jo Knight, Scott Piao, John Mariani, Paul Rayson, and Keith Suderman. 2020. Infrastructure for Semantic Annotation in the Genomics Domain. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6921–6929, Marseille, France. European Language Resources Association.