@inproceedings{cholakov-etal-2014-lexical,
title = "Lexical Substitution Dataset for {G}erman",
author = "Cholakov, Kostadin and
Biemann, Chris and
Eckle-Kohler, Judith and
Gurevych, Iryna",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/545_Paper.pdf",
pages = "1406--1411",
abstract = "This article describes a lexical substitution dataset for German. The whole dataset contains 2,040 sentences from the German Wikipedia, with one target word in each sentence. There are 51 target nouns, 51 adjectives, and 51 verbs randomly selected from 3 frequency groups based on the lemma frequency list of the German WaCKy corpus. 200 sentences have been annotated by 4 professional annotators and the remaining sentences by 1 professional annotator and 5 additional annotators who have been recruited via crowdsourcing. The resulting dataset can be used to evaluate not only lexical substitution systems, but also different sense inventories and word sense disambiguation systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cholakov-etal-2014-lexical">
<titleInfo>
<title>Lexical Substitution Dataset for German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kostadin</namePart>
<namePart type="family">Cholakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Eckle-Kohler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes a lexical substitution dataset for German. The whole dataset contains 2,040 sentences from the German Wikipedia, with one target word in each sentence. There are 51 target nouns, 51 adjectives, and 51 verbs randomly selected from 3 frequency groups based on the lemma frequency list of the German WaCKy corpus. 200 sentences have been annotated by 4 professional annotators and the remaining sentences by 1 professional annotator and 5 additional annotators who have been recruited via crowdsourcing. The resulting dataset can be used to evaluate not only lexical substitution systems, but also different sense inventories and word sense disambiguation systems.</abstract>
<identifier type="citekey">cholakov-etal-2014-lexical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/545_Paper.pdf</url>
</location>
<part>
<date>2014-may</date>
<extent unit="page">
<start>1406</start>
<end>1411</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexical Substitution Dataset for German
%A Cholakov, Kostadin
%A Biemann, Chris
%A Eckle-Kohler, Judith
%A Gurevych, Iryna
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 may
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F cholakov-etal-2014-lexical
%X This article describes a lexical substitution dataset for German. The whole dataset contains 2,040 sentences from the German Wikipedia, with one target word in each sentence. There are 51 target nouns, 51 adjectives, and 51 verbs randomly selected from 3 frequency groups based on the lemma frequency list of the German WaCKy corpus. 200 sentences have been annotated by 4 professional annotators and the remaining sentences by 1 professional annotator and 5 additional annotators who have been recruited via crowdsourcing. The resulting dataset can be used to evaluate not only lexical substitution systems, but also different sense inventories and word sense disambiguation systems.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/545_Paper.pdf
%P 1406-1411
Markdown (Informal)
[Lexical Substitution Dataset for German](http://www.lrec-conf.org/proceedings/lrec2014/pdf/545_Paper.pdf) (Cholakov et al., LREC 2014)
ACL
- Kostadin Cholakov, Chris Biemann, Judith Eckle-Kohler, and Iryna Gurevych. 2014. Lexical Substitution Dataset for German. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1406–1411, Reykjavik, Iceland. European Language Resources Association (ELRA).