@inproceedings{rosen-etal-2016-mwes,
title = "{MWE}s in Treebanks: From Survey to Guidelines",
author = "Ros{\'e}n, Victoria and
De Smedt, Koenraad and
Losnegaard, Gyri Sm{\o}rdal and
Bej{\v{c}}ek, Eduard and
Savary, Agata and
Osenova, Petya",
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/L16-1368",
pages = "2323--2330",
abstract = "By means of an online survey, we have investigated ways in which various types of multiword expressions are annotated in existing treebanks. The results indicate that there is considerable variation in treatments across treebanks and thereby also, to some extent, across languages and across theoretical frameworks. The comparison is focused on the annotation of light verb constructions and verbal idioms. The survey shows that the light verb constructions either get special annotations as such, or are treated as ordinary verbs, while VP idioms are handled through different strategies. Based on insights from our investigation, we propose some general guidelines for annotating multiword expressions in treebanks. The recommendations address the following application-based needs: distinguishing MWEs from similar but compositional constructions; searching distinct types of MWEs in treebanks; awareness of literal and nonliteral meanings; and normalization of the MWE representation. The cross-lingually and cross-theoretically focused survey is intended as an aid to accessing treebanks and an aid for further work on treebank annotation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosen-etal-2016-mwes">
<titleInfo>
<title>MWEs in Treebanks: From Survey to Guidelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Rosén</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koenraad</namePart>
<namePart type="family">De Smedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gyri</namePart>
<namePart type="given">Smørdal</namePart>
<namePart type="family">Losnegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Bejček</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</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>By means of an online survey, we have investigated ways in which various types of multiword expressions are annotated in existing treebanks. The results indicate that there is considerable variation in treatments across treebanks and thereby also, to some extent, across languages and across theoretical frameworks. The comparison is focused on the annotation of light verb constructions and verbal idioms. The survey shows that the light verb constructions either get special annotations as such, or are treated as ordinary verbs, while VP idioms are handled through different strategies. Based on insights from our investigation, we propose some general guidelines for annotating multiword expressions in treebanks. The recommendations address the following application-based needs: distinguishing MWEs from similar but compositional constructions; searching distinct types of MWEs in treebanks; awareness of literal and nonliteral meanings; and normalization of the MWE representation. The cross-lingually and cross-theoretically focused survey is intended as an aid to accessing treebanks and an aid for further work on treebank annotation.</abstract>
<identifier type="citekey">rosen-etal-2016-mwes</identifier>
<location>
<url>https://aclanthology.org/L16-1368</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2323</start>
<end>2330</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MWEs in Treebanks: From Survey to Guidelines
%A Rosén, Victoria
%A De Smedt, Koenraad
%A Losnegaard, Gyri Smørdal
%A Bejček, Eduard
%A Savary, Agata
%A Osenova, Petya
%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 rosen-etal-2016-mwes
%X By means of an online survey, we have investigated ways in which various types of multiword expressions are annotated in existing treebanks. The results indicate that there is considerable variation in treatments across treebanks and thereby also, to some extent, across languages and across theoretical frameworks. The comparison is focused on the annotation of light verb constructions and verbal idioms. The survey shows that the light verb constructions either get special annotations as such, or are treated as ordinary verbs, while VP idioms are handled through different strategies. Based on insights from our investigation, we propose some general guidelines for annotating multiword expressions in treebanks. The recommendations address the following application-based needs: distinguishing MWEs from similar but compositional constructions; searching distinct types of MWEs in treebanks; awareness of literal and nonliteral meanings; and normalization of the MWE representation. The cross-lingually and cross-theoretically focused survey is intended as an aid to accessing treebanks and an aid for further work on treebank annotation.
%U https://aclanthology.org/L16-1368
%P 2323-2330
Markdown (Informal)
[MWEs in Treebanks: From Survey to Guidelines](https://aclanthology.org/L16-1368) (Rosén et al., LREC 2016)
ACL
- Victoria Rosén, Koenraad De Smedt, Gyri Smørdal Losnegaard, Eduard Bejček, Agata Savary, and Petya Osenova. 2016. MWEs in Treebanks: From Survey to Guidelines. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2323–2330, Portorož, Slovenia. European Language Resources Association (ELRA).