@inproceedings{pedersen-etal-2023-da,
title = "The {DA}-{ELEXIS} Corpus - a Sense-Annotated Corpus for {D}anish with Parallel Annotations for Nine {E}uropean Languages",
author = {Pedersen, Bolette and
Nimb, Sanni and
Olsen, Sussi and
Troelsg{\aa}rd, Thomas and
Fl{\"o}rke, Ida and
Jensen, Jonas and
Lorentzen, Henrik},
editor = "Ilinykh, Nikolai and
Morger, Felix and
Dann{\'e}lls, Dana and
Dobnik, Simon and
Megyesi, Be{\'a}ta and
Nivre, Joakim",
booktitle = "Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)",
month = may,
year = "2023",
address = "T{\'o}rshavn, the Faroe Islands",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.resourceful-1.2",
pages = "11--18",
abstract = "In this paper, we present the newly compiled DA-ELEXIS Corpus, which is one of the largest sense-annotated corpora available for Danish, and the first one to be annotated with the Danish wordnet, DanNet. The corpus is part of a European initiative, the ELEXIS project, and has corresponding parallel annotations in nine other European languages. As such it functions as a cross-lingual evaluative benchmark for a series of low and medium resourced European language. We focus here on the Danish annotation process, i.e. on the annotation scheme including annotation guidelines and a primary sense inventory constituted by DanNet as well as the fall-back sense inventory namely The Danish Dictionary (DDO). We analyse and discuss issues such as out of vocabulary (OOV) problems, problems with sense granularity and missing senses (in particular for verbs), and how to semantically tag multiword expressions (MWE), which prove to occur very frequently in the Danish corpus. Finally, we calculate the inter-annotator agreement (IAA) and show how IAA has improved during the annotation process. The openly available corpus contains 32,524 tokens of which sense annotations are given for all content words, amounting to 7,322 nouns, 3,099 verbs, 2,626 adjectives, and 1,677 adverbs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pedersen-etal-2023-da">
<titleInfo>
<title>The DA-ELEXIS Corpus - a Sense-Annotated Corpus for Danish with Parallel Annotations for Nine European Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bolette</namePart>
<namePart type="family">Pedersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanni</namePart>
<namePart type="family">Nimb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sussi</namePart>
<namePart type="family">Olsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Troelsgård</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ida</namePart>
<namePart type="family">Flörke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Jensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrik</namePart>
<namePart type="family">Lorentzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beáta</namePart>
<namePart type="family">Megyesi</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tórshavn, the Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present the newly compiled DA-ELEXIS Corpus, which is one of the largest sense-annotated corpora available for Danish, and the first one to be annotated with the Danish wordnet, DanNet. The corpus is part of a European initiative, the ELEXIS project, and has corresponding parallel annotations in nine other European languages. As such it functions as a cross-lingual evaluative benchmark for a series of low and medium resourced European language. We focus here on the Danish annotation process, i.e. on the annotation scheme including annotation guidelines and a primary sense inventory constituted by DanNet as well as the fall-back sense inventory namely The Danish Dictionary (DDO). We analyse and discuss issues such as out of vocabulary (OOV) problems, problems with sense granularity and missing senses (in particular for verbs), and how to semantically tag multiword expressions (MWE), which prove to occur very frequently in the Danish corpus. Finally, we calculate the inter-annotator agreement (IAA) and show how IAA has improved during the annotation process. The openly available corpus contains 32,524 tokens of which sense annotations are given for all content words, amounting to 7,322 nouns, 3,099 verbs, 2,626 adjectives, and 1,677 adverbs.</abstract>
<identifier type="citekey">pedersen-etal-2023-da</identifier>
<location>
<url>https://aclanthology.org/2023.resourceful-1.2</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>11</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The DA-ELEXIS Corpus - a Sense-Annotated Corpus for Danish with Parallel Annotations for Nine European Languages
%A Pedersen, Bolette
%A Nimb, Sanni
%A Olsen, Sussi
%A Troelsgård, Thomas
%A Flörke, Ida
%A Jensen, Jonas
%A Lorentzen, Henrik
%Y Ilinykh, Nikolai
%Y Morger, Felix
%Y Dannélls, Dana
%Y Dobnik, Simon
%Y Megyesi, Beáta
%Y Nivre, Joakim
%S Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Tórshavn, the Faroe Islands
%F pedersen-etal-2023-da
%X In this paper, we present the newly compiled DA-ELEXIS Corpus, which is one of the largest sense-annotated corpora available for Danish, and the first one to be annotated with the Danish wordnet, DanNet. The corpus is part of a European initiative, the ELEXIS project, and has corresponding parallel annotations in nine other European languages. As such it functions as a cross-lingual evaluative benchmark for a series of low and medium resourced European language. We focus here on the Danish annotation process, i.e. on the annotation scheme including annotation guidelines and a primary sense inventory constituted by DanNet as well as the fall-back sense inventory namely The Danish Dictionary (DDO). We analyse and discuss issues such as out of vocabulary (OOV) problems, problems with sense granularity and missing senses (in particular for verbs), and how to semantically tag multiword expressions (MWE), which prove to occur very frequently in the Danish corpus. Finally, we calculate the inter-annotator agreement (IAA) and show how IAA has improved during the annotation process. The openly available corpus contains 32,524 tokens of which sense annotations are given for all content words, amounting to 7,322 nouns, 3,099 verbs, 2,626 adjectives, and 1,677 adverbs.
%U https://aclanthology.org/2023.resourceful-1.2
%P 11-18
Markdown (Informal)
[The DA-ELEXIS Corpus - a Sense-Annotated Corpus for Danish with Parallel Annotations for Nine European Languages](https://aclanthology.org/2023.resourceful-1.2) (Pedersen et al., RESOURCEFUL 2023)
ACL