@inproceedings{cibej-etal-2024-annotation,
title = "Annotation of Multiword Expressions in the {SUK} 1.0 Training Corpus of {S}lovene: Lessons Learned and Future Steps",
author = "{\v{C}}ibej, Jaka and
Gantar, Polona and
Bon, Mija",
editor = {Bhatia, Archna and
Bouma, Gosse and
Do{\u{g}}ru{\"o}z, A. Seza and
Evang, Kilian and
Garcia, Marcos and
Giouli, Voula and
Han, Lifeng and
Nivre, Joakim and
Rademaker, Alexandre},
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.mwe-1.20",
pages = "154--162",
abstract = "Recent progress within the UniDive COST Action on the compilation of universal guidelines for the annotation of non-verbal multiword expressions (MWEs) has provided an opportunity to improve and expand the work previously done within the PARSEME COST Action on the annotation of verbal multiword expressions in the SUK 1.0 Training Corpus of Slovene. A segment of the training corpus had already been annotated with verbal MWEs during PARSEME. As a follow-up and part of the New Grammar of Modern Standard Slovene (NSSSS) project, the same segment was annotated with non verbal MWEs, resulting in approximately 6, 500 sentences annotated by at least three annotators (described in Gantar et al., 2019). Since then, the entire SUK 1.0 was also manually annotated with UD part-of-speech tags. In the paper, we present an analysis of the MWE annotations exported from the corpus along with their part-of-speech structures through the lens of Universal Dependencies. We discuss the usefulness of the data in terms of potential insight for the further compilation and fine-tuning of guidelines particularly for non-verbal MWEs, and conclude with our plans for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cibej-etal-2024-annotation">
<titleInfo>
<title>Annotation of Multiword Expressions in the SUK 1.0 Training Corpus of Slovene: Lessons Learned and Future Steps</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaka</namePart>
<namePart type="family">Čibej</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Polona</namePart>
<namePart type="family">Gantar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mija</namePart>
<namePart type="family">Bon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Archna</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gosse</namePart>
<namePart type="family">Bouma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Voula</namePart>
<namePart type="family">Giouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent progress within the UniDive COST Action on the compilation of universal guidelines for the annotation of non-verbal multiword expressions (MWEs) has provided an opportunity to improve and expand the work previously done within the PARSEME COST Action on the annotation of verbal multiword expressions in the SUK 1.0 Training Corpus of Slovene. A segment of the training corpus had already been annotated with verbal MWEs during PARSEME. As a follow-up and part of the New Grammar of Modern Standard Slovene (NSSSS) project, the same segment was annotated with non verbal MWEs, resulting in approximately 6, 500 sentences annotated by at least three annotators (described in Gantar et al., 2019). Since then, the entire SUK 1.0 was also manually annotated with UD part-of-speech tags. In the paper, we present an analysis of the MWE annotations exported from the corpus along with their part-of-speech structures through the lens of Universal Dependencies. We discuss the usefulness of the data in terms of potential insight for the further compilation and fine-tuning of guidelines particularly for non-verbal MWEs, and conclude with our plans for future work.</abstract>
<identifier type="citekey">cibej-etal-2024-annotation</identifier>
<location>
<url>https://aclanthology.org/2024.mwe-1.20</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>154</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotation of Multiword Expressions in the SUK 1.0 Training Corpus of Slovene: Lessons Learned and Future Steps
%A Čibej, Jaka
%A Gantar, Polona
%A Bon, Mija
%Y Bhatia, Archna
%Y Bouma, Gosse
%Y Doğruöz, A. Seza
%Y Evang, Kilian
%Y Garcia, Marcos
%Y Giouli, Voula
%Y Han, Lifeng
%Y Nivre, Joakim
%Y Rademaker, Alexandre
%S Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F cibej-etal-2024-annotation
%X Recent progress within the UniDive COST Action on the compilation of universal guidelines for the annotation of non-verbal multiword expressions (MWEs) has provided an opportunity to improve and expand the work previously done within the PARSEME COST Action on the annotation of verbal multiword expressions in the SUK 1.0 Training Corpus of Slovene. A segment of the training corpus had already been annotated with verbal MWEs during PARSEME. As a follow-up and part of the New Grammar of Modern Standard Slovene (NSSSS) project, the same segment was annotated with non verbal MWEs, resulting in approximately 6, 500 sentences annotated by at least three annotators (described in Gantar et al., 2019). Since then, the entire SUK 1.0 was also manually annotated with UD part-of-speech tags. In the paper, we present an analysis of the MWE annotations exported from the corpus along with their part-of-speech structures through the lens of Universal Dependencies. We discuss the usefulness of the data in terms of potential insight for the further compilation and fine-tuning of guidelines particularly for non-verbal MWEs, and conclude with our plans for future work.
%U https://aclanthology.org/2024.mwe-1.20
%P 154-162
Markdown (Informal)
[Annotation of Multiword Expressions in the SUK 1.0 Training Corpus of Slovene: Lessons Learned and Future Steps](https://aclanthology.org/2024.mwe-1.20) (Čibej et al., MWE-UDW-WS 2024)
ACL