@inproceedings{laba-etal-2023-contextual,
title = "Contextual Embeddings for {U}krainian: A Large Language Model Approach to Word Sense Disambiguation",
author = "Laba, Yurii and
Mudryi, Volodymyr and
Chaplynskyi, Dmytro and
Romanyshyn, Mariana and
Dobosevych, Oles",
editor = "Romanyshyn, Mariana",
booktitle = "Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.unlp-1.2",
doi = "10.18653/v1/2023.unlp-1.2",
pages = "11--19",
abstract = "This research proposes a novel approach to the Word Sense Disambiguation (WSD) task in the Ukrainian language based on supervised fine-tuning of a pre-trained Large Language Model (LLM) on the dataset generated in an unsupervised way to obtain better contextual embeddings for words with multiple senses. The paper presents a method for generating a new dataset for WSD evaluation in the Ukrainian language based on the SUM dictionary. We developed a comprehensive framework that facilitates the generation of WSD evaluation datasets, enables the use of different prediction strategies, LLMs, and pooling strategies, and generates multiple performance reports. Our approach shows 77,9{\%} accuracy for lexical meaning prediction for homonyms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laba-etal-2023-contextual">
<titleInfo>
<title>Contextual Embeddings for Ukrainian: A Large Language Model Approach to Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yurii</namePart>
<namePart type="family">Laba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Volodymyr</namePart>
<namePart type="family">Mudryi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmytro</namePart>
<namePart type="family">Chaplynskyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oles</namePart>
<namePart type="family">Dobosevych</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 Ukrainian Natural Language Processing Workshop (UNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This research proposes a novel approach to the Word Sense Disambiguation (WSD) task in the Ukrainian language based on supervised fine-tuning of a pre-trained Large Language Model (LLM) on the dataset generated in an unsupervised way to obtain better contextual embeddings for words with multiple senses. The paper presents a method for generating a new dataset for WSD evaluation in the Ukrainian language based on the SUM dictionary. We developed a comprehensive framework that facilitates the generation of WSD evaluation datasets, enables the use of different prediction strategies, LLMs, and pooling strategies, and generates multiple performance reports. Our approach shows 77,9% accuracy for lexical meaning prediction for homonyms.</abstract>
<identifier type="citekey">laba-etal-2023-contextual</identifier>
<identifier type="doi">10.18653/v1/2023.unlp-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.unlp-1.2</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>11</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contextual Embeddings for Ukrainian: A Large Language Model Approach to Word Sense Disambiguation
%A Laba, Yurii
%A Mudryi, Volodymyr
%A Chaplynskyi, Dmytro
%A Romanyshyn, Mariana
%A Dobosevych, Oles
%Y Romanyshyn, Mariana
%S Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F laba-etal-2023-contextual
%X This research proposes a novel approach to the Word Sense Disambiguation (WSD) task in the Ukrainian language based on supervised fine-tuning of a pre-trained Large Language Model (LLM) on the dataset generated in an unsupervised way to obtain better contextual embeddings for words with multiple senses. The paper presents a method for generating a new dataset for WSD evaluation in the Ukrainian language based on the SUM dictionary. We developed a comprehensive framework that facilitates the generation of WSD evaluation datasets, enables the use of different prediction strategies, LLMs, and pooling strategies, and generates multiple performance reports. Our approach shows 77,9% accuracy for lexical meaning prediction for homonyms.
%R 10.18653/v1/2023.unlp-1.2
%U https://aclanthology.org/2023.unlp-1.2
%U https://doi.org/10.18653/v1/2023.unlp-1.2
%P 11-19
Markdown (Informal)
[Contextual Embeddings for Ukrainian: A Large Language Model Approach to Word Sense Disambiguation](https://aclanthology.org/2023.unlp-1.2) (Laba et al., UNLP 2023)
ACL