@inproceedings{pedersen-etal-2022-compiling,
title = "Compiling a Suitable Level of Sense Granularity in a Lexicon for {AI} Purposes: The Open Source {COR} Lexicon",
author = "Pedersen, Bolette and
S{\o}rensen, Nathalie Carmen Hau and
Nimb, Sanni and
Fl{\o}rke, Ida and
Olsen, Sussi and
Troelsg{\aa}rd, Thomas",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.6",
pages = "51--60",
abstract = "We present The Central Word Register for Danish (COR), which is an open source lexicon project for general AI purposes funded and initiated by the Danish Agency for Digitisation as part of an AI initiative embarked by the Danish Government in 2020. We focus here on the lexical semantic part of the project (COR-S) and describe how we {--} based on the existing fine-grained sense inventory from Den Danske Ordbog (DDO) {--} compile a more AI suitable sense granularity level of the vocabulary. A three-step methodology is applied: We establish a set of linguistic principles for defining core senses in COR-S and from there, we generate a hand-crafted gold standard of 6,000 lemmas depicting how to come from the fine-grained DDO sense to the COR inventory. Finally, we experiment with a number of language models in order to automatize the sense reduction of the rest of the lexicon. The models comprise a ruled-based model that applies our linguistic principles in terms of features, a word2vec model using cosine similarity to measure the sense proximity, and finally a deep neural BERT model fine-tuned on our annotations. The rule-based approach shows best results, in particular on adjectives, however, when focusing on the average polysemous vocabulary, the BERT model shows promising results too.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pedersen-etal-2022-compiling">
<titleInfo>
<title>Compiling a Suitable Level of Sense Granularity in a Lexicon for AI Purposes: The Open Source COR Lexicon</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">Nathalie</namePart>
<namePart type="given">Carmen</namePart>
<namePart type="given">Hau</namePart>
<namePart type="family">Sørensen</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">Ida</namePart>
<namePart type="family">Flørke</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>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present The Central Word Register for Danish (COR), which is an open source lexicon project for general AI purposes funded and initiated by the Danish Agency for Digitisation as part of an AI initiative embarked by the Danish Government in 2020. We focus here on the lexical semantic part of the project (COR-S) and describe how we – based on the existing fine-grained sense inventory from Den Danske Ordbog (DDO) – compile a more AI suitable sense granularity level of the vocabulary. A three-step methodology is applied: We establish a set of linguistic principles for defining core senses in COR-S and from there, we generate a hand-crafted gold standard of 6,000 lemmas depicting how to come from the fine-grained DDO sense to the COR inventory. Finally, we experiment with a number of language models in order to automatize the sense reduction of the rest of the lexicon. The models comprise a ruled-based model that applies our linguistic principles in terms of features, a word2vec model using cosine similarity to measure the sense proximity, and finally a deep neural BERT model fine-tuned on our annotations. The rule-based approach shows best results, in particular on adjectives, however, when focusing on the average polysemous vocabulary, the BERT model shows promising results too.</abstract>
<identifier type="citekey">pedersen-etal-2022-compiling</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.6</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>51</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Compiling a Suitable Level of Sense Granularity in a Lexicon for AI Purposes: The Open Source COR Lexicon
%A Pedersen, Bolette
%A Sørensen, Nathalie Carmen Hau
%A Nimb, Sanni
%A Flørke, Ida
%A Olsen, Sussi
%A Troelsgård, Thomas
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F pedersen-etal-2022-compiling
%X We present The Central Word Register for Danish (COR), which is an open source lexicon project for general AI purposes funded and initiated by the Danish Agency for Digitisation as part of an AI initiative embarked by the Danish Government in 2020. We focus here on the lexical semantic part of the project (COR-S) and describe how we – based on the existing fine-grained sense inventory from Den Danske Ordbog (DDO) – compile a more AI suitable sense granularity level of the vocabulary. A three-step methodology is applied: We establish a set of linguistic principles for defining core senses in COR-S and from there, we generate a hand-crafted gold standard of 6,000 lemmas depicting how to come from the fine-grained DDO sense to the COR inventory. Finally, we experiment with a number of language models in order to automatize the sense reduction of the rest of the lexicon. The models comprise a ruled-based model that applies our linguistic principles in terms of features, a word2vec model using cosine similarity to measure the sense proximity, and finally a deep neural BERT model fine-tuned on our annotations. The rule-based approach shows best results, in particular on adjectives, however, when focusing on the average polysemous vocabulary, the BERT model shows promising results too.
%U https://aclanthology.org/2022.lrec-1.6
%P 51-60
Markdown (Informal)
[Compiling a Suitable Level of Sense Granularity in a Lexicon for AI Purposes: The Open Source COR Lexicon](https://aclanthology.org/2022.lrec-1.6) (Pedersen et al., LREC 2022)
ACL