@inproceedings{orasmaa-etal-2010-information,
title = "Information Retrieval of Word Form Variants in Spoken Language Corpora Using Generalized Edit Distance",
author = {Orasmaa, Siim and
K{\"a}{\"a}rik, Reina and
Vilo, Jaak and
Hennoste, Tiit},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/600_Paper.pdf",
abstract = "An important feature of spoken language corpora is existence of different spelling variants of words in transcription. So there is an important problem for linguist who works with large spoken corpora: how to find all variants of the word without annotating them manually? Our work describes a search engine that enables finding different spelling variants (true positives) from corpus of spoken language, and reduces efficiently the amount of false positives returned during the search. Our search engine uses a generalized variant of the edit distance algorithm that allows defining text-specific string to string transformations in addition to the default edit operations defined in edit distance. We have extended our algorithm with capability to block transformations in specific substrings of search words. User can mark certain regions (blocked regions) of the search word where edit operations are not allowed. Our material comes from the Corpus of Spoken Estonian of the University of Tartu which consists of about 2000 dialogues and texts, about 1.4 million running text units in total.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="orasmaa-etal-2010-information">
<titleInfo>
<title>Information Retrieval of Word Form Variants in Spoken Language Corpora Using Generalized Edit Distance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siim</namePart>
<namePart type="family">Orasmaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reina</namePart>
<namePart type="family">Käärik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaak</namePart>
<namePart type="family">Vilo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiit</namePart>
<namePart type="family">Hennoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>An important feature of spoken language corpora is existence of different spelling variants of words in transcription. So there is an important problem for linguist who works with large spoken corpora: how to find all variants of the word without annotating them manually? Our work describes a search engine that enables finding different spelling variants (true positives) from corpus of spoken language, and reduces efficiently the amount of false positives returned during the search. Our search engine uses a generalized variant of the edit distance algorithm that allows defining text-specific string to string transformations in addition to the default edit operations defined in edit distance. We have extended our algorithm with capability to block transformations in specific substrings of search words. User can mark certain regions (blocked regions) of the search word where edit operations are not allowed. Our material comes from the Corpus of Spoken Estonian of the University of Tartu which consists of about 2000 dialogues and texts, about 1.4 million running text units in total.</abstract>
<identifier type="citekey">orasmaa-etal-2010-information</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/600_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Information Retrieval of Word Form Variants in Spoken Language Corpora Using Generalized Edit Distance
%A Orasmaa, Siim
%A Käärik, Reina
%A Vilo, Jaak
%A Hennoste, Tiit
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F orasmaa-etal-2010-information
%X An important feature of spoken language corpora is existence of different spelling variants of words in transcription. So there is an important problem for linguist who works with large spoken corpora: how to find all variants of the word without annotating them manually? Our work describes a search engine that enables finding different spelling variants (true positives) from corpus of spoken language, and reduces efficiently the amount of false positives returned during the search. Our search engine uses a generalized variant of the edit distance algorithm that allows defining text-specific string to string transformations in addition to the default edit operations defined in edit distance. We have extended our algorithm with capability to block transformations in specific substrings of search words. User can mark certain regions (blocked regions) of the search word where edit operations are not allowed. Our material comes from the Corpus of Spoken Estonian of the University of Tartu which consists of about 2000 dialogues and texts, about 1.4 million running text units in total.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/600_Paper.pdf
Markdown (Informal)
[Information Retrieval of Word Form Variants in Spoken Language Corpora Using Generalized Edit Distance](http://www.lrec-conf.org/proceedings/lrec2010/pdf/600_Paper.pdf) (Orasmaa et al., LREC 2010)
ACL