@inproceedings{krstev-etal-2024-towards,
title = "Towards the semantic annotation of {SR}-{ELEXIS} corpus: Insights into Multiword Expressions and Named Entities",
author = "Krstev, Cvetana and
Stankovi{\'c}, Ranka and
Markovi{\'c}, Aleksandra M. and
Mihajlov, Teodora Sofija",
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-1.15",
pages = "106--114",
abstract = "This paper presents the work in progress on ELEXIS-sr corpus, the Serbian addition to the ELEXIS multilingual annotated corpus ElexisWSD, comprising semantic annotations and word sense repositories. The ELEXIS corpus has parallel annotations in ten European languages, serving as a cross-lingual benchmark for evaluating low and medium-resourced European languages. The focus in this paper is on multiword expressions (MWEs) and named entities (NEs), their recognition in the ELEXIS-sr sentence set, and comparison with annotations in other languages. The first steps in building the Serbian sense inventory are discussed, and some results concerning MWEs and NEs are analysed. Once completed, the ELEXIS-sr corpus will be the first sense annotated corpus using the Serbian WordNet (SrpWN). Finally, ideas to represent MWE lexicon entries as Linguistic Linked-Open Data (LLOD) and connect them with occurrences in the corpus are presented.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krstev-etal-2024-towards">
<titleInfo>
<title>Towards the semantic annotation of SR-ELEXIS corpus: Insights into Multiword Expressions and Named Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cvetana</namePart>
<namePart type="family">Krstev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ranka</namePart>
<namePart type="family">Stanković</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Marković</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teodora</namePart>
<namePart type="given">Sofija</namePart>
<namePart type="family">Mihajlov</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>This paper presents the work in progress on ELEXIS-sr corpus, the Serbian addition to the ELEXIS multilingual annotated corpus ElexisWSD, comprising semantic annotations and word sense repositories. The ELEXIS corpus has parallel annotations in ten European languages, serving as a cross-lingual benchmark for evaluating low and medium-resourced European languages. The focus in this paper is on multiword expressions (MWEs) and named entities (NEs), their recognition in the ELEXIS-sr sentence set, and comparison with annotations in other languages. The first steps in building the Serbian sense inventory are discussed, and some results concerning MWEs and NEs are analysed. Once completed, the ELEXIS-sr corpus will be the first sense annotated corpus using the Serbian WordNet (SrpWN). Finally, ideas to represent MWE lexicon entries as Linguistic Linked-Open Data (LLOD) and connect them with occurrences in the corpus are presented.</abstract>
<identifier type="citekey">krstev-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.mwe-1.15</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>106</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards the semantic annotation of SR-ELEXIS corpus: Insights into Multiword Expressions and Named Entities
%A Krstev, Cvetana
%A Stanković, Ranka
%A Marković, Aleksandra M.
%A Mihajlov, Teodora Sofija
%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 krstev-etal-2024-towards
%X This paper presents the work in progress on ELEXIS-sr corpus, the Serbian addition to the ELEXIS multilingual annotated corpus ElexisWSD, comprising semantic annotations and word sense repositories. The ELEXIS corpus has parallel annotations in ten European languages, serving as a cross-lingual benchmark for evaluating low and medium-resourced European languages. The focus in this paper is on multiword expressions (MWEs) and named entities (NEs), their recognition in the ELEXIS-sr sentence set, and comparison with annotations in other languages. The first steps in building the Serbian sense inventory are discussed, and some results concerning MWEs and NEs are analysed. Once completed, the ELEXIS-sr corpus will be the first sense annotated corpus using the Serbian WordNet (SrpWN). Finally, ideas to represent MWE lexicon entries as Linguistic Linked-Open Data (LLOD) and connect them with occurrences in the corpus are presented.
%U https://aclanthology.org/2024.mwe-1.15
%P 106-114
Markdown (Informal)
[Towards the semantic annotation of SR-ELEXIS corpus: Insights into Multiword Expressions and Named Entities](https://aclanthology.org/2024.mwe-1.15) (Krstev et al., MWE-UDW-WS 2024)
ACL