@inproceedings{maynard-greenwood-2012-large,
title = "Large Scale Semantic Annotation, Indexing and Search at The National Archives",
author = "Maynard, Diana and
Greenwood, Mark A.",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/122_Paper.pdf",
pages = "3487--3494",
abstract = "This paper describes a tool developed to improve access to the enormous volume of data housed at the UK's National Archives, both for the general public and for specialist researchers. The system we have developed, TNA-Search, enables a multi-paradigm search over the entire electronic archive (42TB of data in various formats). The search functionality allows queries that arbitrarily mix any combination of full-text, structural, linguistic and semantic queries. The archive is annotated and indexed with respect to a massive semantic knowledge base containing data from the LOD cloud, data.gov.uk, related TNA projects, and a large geographical database. The semantic annotation component achieves approximately 83{\%} F-measure, which is very reasonable considering the wide range of entities and document types and the open domain. The technologies are being adopted by real users at The National Archives and will form the core of their suite of search tools, with additional in-house interfaces.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maynard-greenwood-2012-large">
<titleInfo>
<title>Large Scale Semantic Annotation, Indexing and Search at The National Archives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Maynard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Greenwood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a tool developed to improve access to the enormous volume of data housed at the UK’s National Archives, both for the general public and for specialist researchers. The system we have developed, TNA-Search, enables a multi-paradigm search over the entire electronic archive (42TB of data in various formats). The search functionality allows queries that arbitrarily mix any combination of full-text, structural, linguistic and semantic queries. The archive is annotated and indexed with respect to a massive semantic knowledge base containing data from the LOD cloud, data.gov.uk, related TNA projects, and a large geographical database. The semantic annotation component achieves approximately 83% F-measure, which is very reasonable considering the wide range of entities and document types and the open domain. The technologies are being adopted by real users at The National Archives and will form the core of their suite of search tools, with additional in-house interfaces.</abstract>
<identifier type="citekey">maynard-greenwood-2012-large</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/122_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3487</start>
<end>3494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Scale Semantic Annotation, Indexing and Search at The National Archives
%A Maynard, Diana
%A Greenwood, Mark A.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F maynard-greenwood-2012-large
%X This paper describes a tool developed to improve access to the enormous volume of data housed at the UK’s National Archives, both for the general public and for specialist researchers. The system we have developed, TNA-Search, enables a multi-paradigm search over the entire electronic archive (42TB of data in various formats). The search functionality allows queries that arbitrarily mix any combination of full-text, structural, linguistic and semantic queries. The archive is annotated and indexed with respect to a massive semantic knowledge base containing data from the LOD cloud, data.gov.uk, related TNA projects, and a large geographical database. The semantic annotation component achieves approximately 83% F-measure, which is very reasonable considering the wide range of entities and document types and the open domain. The technologies are being adopted by real users at The National Archives and will form the core of their suite of search tools, with additional in-house interfaces.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/122_Paper.pdf
%P 3487-3494
Markdown (Informal)
[Large Scale Semantic Annotation, Indexing and Search at The National Archives](http://www.lrec-conf.org/proceedings/lrec2012/pdf/122_Paper.pdf) (Maynard & Greenwood, LREC 2012)
ACL