@inproceedings{barbu-mititelu-etal-2026-romanian,
title = "The {R}omanian Corpus Annotated with Multiword Expressions. {PARSEME}-Ro Version 2.0",
author = "Barbu Mititelu, Verginica and
Cristescu, Mihaela and
Irimia, Elena and
Vasile, Carmen M{\^i}rzea",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.938/",
doi = "10.63317/3dnsaryv4kdh",
pages = "11979--11991",
abstract = "The Romanian journalistic corpus previously annotated with verbal multiword expressions (PARSEME-Ro) has been extended recently with other journalistic texts and annotated with multiword expressions of all parts of speech closely observing version 2.0 of the PARSEME guidelines. The corpus size has been increased by about 40{\%}, it underwent automatic morpho-syntactic annotation following the Universal Dependencies principles, as well as extensive semi-automatic annotation of multiword expressions of all morphological types (nominal, adjectival, adverbial, determiner, pronominal, prepositional, conjunction, interjection, and verbal for the newly added texts). We present here our work methodology, which involves an automatic annotation phase, but the manual work prevails in checking the annotation and its consistency. We also offer quantitative data about the new version of the corpus, the types of multiword expressions existing in Romanian and occurring therein, and characteristics thereof. The new version of the PARSEME-Ro corpus contributes to the field of developing multiword expressions resources per se, i.e. describing this language phenomenon, as well as resources for training, tuning and testing the performance of tools and large language models when dealing with this linguistic phenomenon.The paper also discusses some remarks on the MWE paraphrasing subtask in which a part of the corpus was used. The corpus is released with a permissive license."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barbu-mititelu-etal-2026-romanian">
<titleInfo>
<title>The Romanian Corpus Annotated with Multiword Expressions. PARSEME-Ro Version 2.0</title>
</titleInfo>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="family">Barbu Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihaela</namePart>
<namePart type="family">Cristescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Irimia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carmen</namePart>
<namePart type="given">Mîrzea</namePart>
<namePart type="family">Vasile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<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">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Romanian journalistic corpus previously annotated with verbal multiword expressions (PARSEME-Ro) has been extended recently with other journalistic texts and annotated with multiword expressions of all parts of speech closely observing version 2.0 of the PARSEME guidelines. The corpus size has been increased by about 40%, it underwent automatic morpho-syntactic annotation following the Universal Dependencies principles, as well as extensive semi-automatic annotation of multiword expressions of all morphological types (nominal, adjectival, adverbial, determiner, pronominal, prepositional, conjunction, interjection, and verbal for the newly added texts). We present here our work methodology, which involves an automatic annotation phase, but the manual work prevails in checking the annotation and its consistency. We also offer quantitative data about the new version of the corpus, the types of multiword expressions existing in Romanian and occurring therein, and characteristics thereof. The new version of the PARSEME-Ro corpus contributes to the field of developing multiword expressions resources per se, i.e. describing this language phenomenon, as well as resources for training, tuning and testing the performance of tools and large language models when dealing with this linguistic phenomenon.The paper also discusses some remarks on the MWE paraphrasing subtask in which a part of the corpus was used. The corpus is released with a permissive license.</abstract>
<identifier type="citekey">barbu-mititelu-etal-2026-romanian</identifier>
<identifier type="doi">10.63317/3dnsaryv4kdh</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.938/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11979</start>
<end>11991</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Romanian Corpus Annotated with Multiword Expressions. PARSEME-Ro Version 2.0
%A Barbu Mititelu, Verginica
%A Cristescu, Mihaela
%A Irimia, Elena
%A Vasile, Carmen Mîrzea
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F barbu-mititelu-etal-2026-romanian
%X The Romanian journalistic corpus previously annotated with verbal multiword expressions (PARSEME-Ro) has been extended recently with other journalistic texts and annotated with multiword expressions of all parts of speech closely observing version 2.0 of the PARSEME guidelines. The corpus size has been increased by about 40%, it underwent automatic morpho-syntactic annotation following the Universal Dependencies principles, as well as extensive semi-automatic annotation of multiword expressions of all morphological types (nominal, adjectival, adverbial, determiner, pronominal, prepositional, conjunction, interjection, and verbal for the newly added texts). We present here our work methodology, which involves an automatic annotation phase, but the manual work prevails in checking the annotation and its consistency. We also offer quantitative data about the new version of the corpus, the types of multiword expressions existing in Romanian and occurring therein, and characteristics thereof. The new version of the PARSEME-Ro corpus contributes to the field of developing multiword expressions resources per se, i.e. describing this language phenomenon, as well as resources for training, tuning and testing the performance of tools and large language models when dealing with this linguistic phenomenon.The paper also discusses some remarks on the MWE paraphrasing subtask in which a part of the corpus was used. The corpus is released with a permissive license.
%R 10.63317/3dnsaryv4kdh
%U https://aclanthology.org/2026.lrec-1.938/
%U https://doi.org/10.63317/3dnsaryv4kdh
%P 11979-11991
Markdown (Informal)
[The Romanian Corpus Annotated with Multiword Expressions. PARSEME-Ro Version 2.0](https://aclanthology.org/2026.lrec-1.938/) (Barbu Mititelu et al., LREC 2026)
ACL