@inproceedings{kettunen-paakkonen-2016-measuring,
title = "Measuring Lexical Quality of a Historical {F}innish Newspaper Collection ― Analysis of Garbled {OCR} Data with Basic Language Technology Tools and Means",
author = {Kettunen, Kimmo and
P{\"a}{\"a}kk{\"o}nen, Tuula},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1152",
pages = "956--961",
abstract = {The National Library of Finland has digitized a large proportion of the historical newspapers published in Finland between 1771 and 1910 (Bremer-Laamanen 2001). This collection contains approximately 1.95 million pages in Finnish and Swedish. Finnish part of the collection consists of about 2.39 billion words. The National Library{'}s Digital Collections are offered via the digi.kansalliskirjasto.fi web service, also known as Digi. Part of this material is also available freely downloadable in The Language Bank of Finland provided by the Fin-CLARIN consortium . The collection can also be accessed through the Korp environment that has been developed by Spr{\"a}kbanken at the University of Gothenburg and extended by FIN-CLARIN team at the University of Helsinki to provide concordances of text resources. A Cranfield-style information retrieval test collection has been produced out of a small part of the Digi newspaper material at the University of Tampere (J{\"a}rvelin et al., 2015). The quality of the OCRed collections is an important topic in digital humanities, as it affects general usability and searchability of collections. There is no single available method to assess the quality of large collections, but different methods can be used to approximate the quality. This paper discusses different corpus analysis style ways to approximate the overall lexical quality of the Finnish part of the Digi collection.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kettunen-paakkonen-2016-measuring">
<titleInfo>
<title>Measuring Lexical Quality of a Historical Finnish Newspaper Collection ― Analysis of Garbled OCR Data with Basic Language Technology Tools and Means</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kimmo</namePart>
<namePart type="family">Kettunen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuula</namePart>
<namePart type="family">Pääkkönen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The National Library of Finland has digitized a large proportion of the historical newspapers published in Finland between 1771 and 1910 (Bremer-Laamanen 2001). This collection contains approximately 1.95 million pages in Finnish and Swedish. Finnish part of the collection consists of about 2.39 billion words. The National Library’s Digital Collections are offered via the digi.kansalliskirjasto.fi web service, also known as Digi. Part of this material is also available freely downloadable in The Language Bank of Finland provided by the Fin-CLARIN consortium . The collection can also be accessed through the Korp environment that has been developed by Spräkbanken at the University of Gothenburg and extended by FIN-CLARIN team at the University of Helsinki to provide concordances of text resources. A Cranfield-style information retrieval test collection has been produced out of a small part of the Digi newspaper material at the University of Tampere (Järvelin et al., 2015). The quality of the OCRed collections is an important topic in digital humanities, as it affects general usability and searchability of collections. There is no single available method to assess the quality of large collections, but different methods can be used to approximate the quality. This paper discusses different corpus analysis style ways to approximate the overall lexical quality of the Finnish part of the Digi collection.</abstract>
<identifier type="citekey">kettunen-paakkonen-2016-measuring</identifier>
<location>
<url>https://aclanthology.org/L16-1152</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>956</start>
<end>961</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Lexical Quality of a Historical Finnish Newspaper Collection ― Analysis of Garbled OCR Data with Basic Language Technology Tools and Means
%A Kettunen, Kimmo
%A Pääkkönen, Tuula
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F kettunen-paakkonen-2016-measuring
%X The National Library of Finland has digitized a large proportion of the historical newspapers published in Finland between 1771 and 1910 (Bremer-Laamanen 2001). This collection contains approximately 1.95 million pages in Finnish and Swedish. Finnish part of the collection consists of about 2.39 billion words. The National Library’s Digital Collections are offered via the digi.kansalliskirjasto.fi web service, also known as Digi. Part of this material is also available freely downloadable in The Language Bank of Finland provided by the Fin-CLARIN consortium . The collection can also be accessed through the Korp environment that has been developed by Spräkbanken at the University of Gothenburg and extended by FIN-CLARIN team at the University of Helsinki to provide concordances of text resources. A Cranfield-style information retrieval test collection has been produced out of a small part of the Digi newspaper material at the University of Tampere (Järvelin et al., 2015). The quality of the OCRed collections is an important topic in digital humanities, as it affects general usability and searchability of collections. There is no single available method to assess the quality of large collections, but different methods can be used to approximate the quality. This paper discusses different corpus analysis style ways to approximate the overall lexical quality of the Finnish part of the Digi collection.
%U https://aclanthology.org/L16-1152
%P 956-961
Markdown (Informal)
[Measuring Lexical Quality of a Historical Finnish Newspaper Collection ― Analysis of Garbled OCR Data with Basic Language Technology Tools and Means](https://aclanthology.org/L16-1152) (Kettunen & Pääkkönen, LREC 2016)
ACL