@inproceedings{strakatova-etal-2020-glitters,
title = "All That Glitters is Not Gold: A Gold Standard of Adjective-Noun Collocations for {G}erman",
author = "Strakatova, Yana and
Falk, Neele and
Fuhrmann, Isabel and
Hinrichs, Erhard and
Rossmann, Daniela",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.538/",
pages = "4368--4378",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "In this paper we present the GerCo dataset of adjective-noun collocations for German, such as alter Freund {\textquoteleft}old friend' and tiefe Liebe {\textquoteleft}deep love'. The annotation has been performed by experts based on the annotation scheme introduced in this paper. The resulting dataset contains 4,732 positive and negative instances of collocations and covers all the 16 semantic classes of adjectives as defined in the German wordnet GermaNet. The dataset can serve as a reliable empirical basis for comparing different theoretical frameworks concerned with collocations or as material for data-driven approaches to the studies of collocations including different machine learning experiments. This paper addresses the latter issue by using the GerCo dataset for evaluating different models on the task of automatic collocation identification. We compare lexical association measures with static and contextualized word embeddings. The experiments show that word embeddings outperform methods based on statistical association measures by a wide margin."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strakatova-etal-2020-glitters">
<titleInfo>
<title>All That Glitters is Not Gold: A Gold Standard of Adjective-Noun Collocations for German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yana</namePart>
<namePart type="family">Strakatova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neele</namePart>
<namePart type="family">Falk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Fuhrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erhard</namePart>
<namePart type="family">Hinrichs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Rossmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper we present the GerCo dataset of adjective-noun collocations for German, such as alter Freund ‘old friend’ and tiefe Liebe ‘deep love’. The annotation has been performed by experts based on the annotation scheme introduced in this paper. The resulting dataset contains 4,732 positive and negative instances of collocations and covers all the 16 semantic classes of adjectives as defined in the German wordnet GermaNet. The dataset can serve as a reliable empirical basis for comparing different theoretical frameworks concerned with collocations or as material for data-driven approaches to the studies of collocations including different machine learning experiments. This paper addresses the latter issue by using the GerCo dataset for evaluating different models on the task of automatic collocation identification. We compare lexical association measures with static and contextualized word embeddings. The experiments show that word embeddings outperform methods based on statistical association measures by a wide margin.</abstract>
<identifier type="citekey">strakatova-etal-2020-glitters</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.538/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4368</start>
<end>4378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T All That Glitters is Not Gold: A Gold Standard of Adjective-Noun Collocations for German
%A Strakatova, Yana
%A Falk, Neele
%A Fuhrmann, Isabel
%A Hinrichs, Erhard
%A Rossmann, Daniela
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F strakatova-etal-2020-glitters
%X In this paper we present the GerCo dataset of adjective-noun collocations for German, such as alter Freund ‘old friend’ and tiefe Liebe ‘deep love’. The annotation has been performed by experts based on the annotation scheme introduced in this paper. The resulting dataset contains 4,732 positive and negative instances of collocations and covers all the 16 semantic classes of adjectives as defined in the German wordnet GermaNet. The dataset can serve as a reliable empirical basis for comparing different theoretical frameworks concerned with collocations or as material for data-driven approaches to the studies of collocations including different machine learning experiments. This paper addresses the latter issue by using the GerCo dataset for evaluating different models on the task of automatic collocation identification. We compare lexical association measures with static and contextualized word embeddings. The experiments show that word embeddings outperform methods based on statistical association measures by a wide margin.
%U https://aclanthology.org/2020.lrec-1.538/
%P 4368-4378
Markdown (Informal)
[All That Glitters is Not Gold: A Gold Standard of Adjective-Noun Collocations for German](https://aclanthology.org/2020.lrec-1.538/) (Strakatova et al., LREC 2020)
ACL