@inproceedings{halskov-etal-2010-quality,
title = "Quality Indicators of {LSP} Texts {---} Selection and Measurements Measuring the Terminological Usefulness of Documents for an {LSP} Corpus",
author = "Halskov, Jakob and
Hansen, Dorte Haltrup and
Braasch, Anna and
Olsen, Sussi",
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/505_Paper.pdf",
abstract = "This paper describes and evaluates a prototype quality assurance system for LSP corpora. The system will be employed in compiling a corpus of 11 M tokens for various linguistic and terminological purposes. The system utilizes a number of linguistic features as quality indicators. These represent two dimensions of quality, namely readability/formality (e.g. word length and passive constructions) and density of specialized knowledge (e.g. out-of-vocabulary items). Threshold values for each indicator are induced from a reference corpus of general (fiction, magazines and newspapers) and specialized language (the domains of Health/Medicine and Environment/Climate). In order to test the efficiency of the indicators, a number of terminologically relevant, irrelevant and possibly relevant texts are manually selected from target web sites as candidate texts. By applying the indicators to these candidate texts, the system is able to filter out non-LSP and poor LSP texts with a precision of 100{\%} and a recall of 55{\%}. Thus, the experiment described in this paper constitutes fundamental work towards a formulation of best practice for implementing quality assurance when selecting appropriate texts for an LSP corpus. The domain independence of the quality indicators still remains to be thoroughly tested on more than just two domains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="halskov-etal-2010-quality">
<titleInfo>
<title>Quality Indicators of LSP Texts — Selection and Measurements Measuring the Terminological Usefulness of Documents for an LSP Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Halskov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorte</namePart>
<namePart type="given">Haltrup</namePart>
<namePart type="family">Hansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Braasch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sussi</namePart>
<namePart type="family">Olsen</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>This paper describes and evaluates a prototype quality assurance system for LSP corpora. The system will be employed in compiling a corpus of 11 M tokens for various linguistic and terminological purposes. The system utilizes a number of linguistic features as quality indicators. These represent two dimensions of quality, namely readability/formality (e.g. word length and passive constructions) and density of specialized knowledge (e.g. out-of-vocabulary items). Threshold values for each indicator are induced from a reference corpus of general (fiction, magazines and newspapers) and specialized language (the domains of Health/Medicine and Environment/Climate). In order to test the efficiency of the indicators, a number of terminologically relevant, irrelevant and possibly relevant texts are manually selected from target web sites as candidate texts. By applying the indicators to these candidate texts, the system is able to filter out non-LSP and poor LSP texts with a precision of 100% and a recall of 55%. Thus, the experiment described in this paper constitutes fundamental work towards a formulation of best practice for implementing quality assurance when selecting appropriate texts for an LSP corpus. The domain independence of the quality indicators still remains to be thoroughly tested on more than just two domains.</abstract>
<identifier type="citekey">halskov-etal-2010-quality</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/505_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quality Indicators of LSP Texts — Selection and Measurements Measuring the Terminological Usefulness of Documents for an LSP Corpus
%A Halskov, Jakob
%A Hansen, Dorte Haltrup
%A Braasch, Anna
%A Olsen, Sussi
%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 halskov-etal-2010-quality
%X This paper describes and evaluates a prototype quality assurance system for LSP corpora. The system will be employed in compiling a corpus of 11 M tokens for various linguistic and terminological purposes. The system utilizes a number of linguistic features as quality indicators. These represent two dimensions of quality, namely readability/formality (e.g. word length and passive constructions) and density of specialized knowledge (e.g. out-of-vocabulary items). Threshold values for each indicator are induced from a reference corpus of general (fiction, magazines and newspapers) and specialized language (the domains of Health/Medicine and Environment/Climate). In order to test the efficiency of the indicators, a number of terminologically relevant, irrelevant and possibly relevant texts are manually selected from target web sites as candidate texts. By applying the indicators to these candidate texts, the system is able to filter out non-LSP and poor LSP texts with a precision of 100% and a recall of 55%. Thus, the experiment described in this paper constitutes fundamental work towards a formulation of best practice for implementing quality assurance when selecting appropriate texts for an LSP corpus. The domain independence of the quality indicators still remains to be thoroughly tested on more than just two domains.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/505_Paper.pdf
Markdown (Informal)
[Quality Indicators of LSP Texts — Selection and Measurements Measuring the Terminological Usefulness of Documents for an LSP Corpus](http://www.lrec-conf.org/proceedings/lrec2010/pdf/505_Paper.pdf) (Halskov et al., LREC 2010)
ACL