@inproceedings{kelious-etal-2024-complex-word,
title = "Complex Word Identification: A Comparative Study between {C}hat{GPT} and a Dedicated Model for This Task",
author = "Kelious, Abdelhak and
Constant, Mathieu and
Coeur, Christophe",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.323",
pages = "3645--3653",
abstract = "There are several works in natural language processing for identifying lexical complexity. This can be for various reasons, either for simplification, the selection of more suitable content, or for other specific tasks. Words can have multiple definitions and degrees of complexity depending on the context in which they appear. One solution being investigated is lexical complexity prediction, where computational methods are used to evaluate the difficulty of vocabulary for language learners and offer personalized assistance. In this work, we explore deep learning methods to assess the complexity of a word based on its context. Specifically, we investigate how to use pre-trained language models to encode both the sentence and the target word, and then fine-tune them by combining them with additional frequency-based features. Our approach achieved superior results compared to the best systems in SemEval-2021 (Shardlow et al., 2021), as demonstrated by an R2 score of 0.65. Finally, we carry out a comparative study with ChatGPT to assess its potential for predicting lexical complexity, to see whether prompt engineering can be an alternative to this task, we will discuss the advantages and limitations of ChatGPT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kelious-etal-2024-complex-word">
<titleInfo>
<title>Complex Word Identification: A Comparative Study between ChatGPT and a Dedicated Model for This Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelhak</namePart>
<namePart type="family">Kelious</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Coeur</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>There are several works in natural language processing for identifying lexical complexity. This can be for various reasons, either for simplification, the selection of more suitable content, or for other specific tasks. Words can have multiple definitions and degrees of complexity depending on the context in which they appear. One solution being investigated is lexical complexity prediction, where computational methods are used to evaluate the difficulty of vocabulary for language learners and offer personalized assistance. In this work, we explore deep learning methods to assess the complexity of a word based on its context. Specifically, we investigate how to use pre-trained language models to encode both the sentence and the target word, and then fine-tune them by combining them with additional frequency-based features. Our approach achieved superior results compared to the best systems in SemEval-2021 (Shardlow et al., 2021), as demonstrated by an R2 score of 0.65. Finally, we carry out a comparative study with ChatGPT to assess its potential for predicting lexical complexity, to see whether prompt engineering can be an alternative to this task, we will discuss the advantages and limitations of ChatGPT.</abstract>
<identifier type="citekey">kelious-etal-2024-complex-word</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.323</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3645</start>
<end>3653</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Complex Word Identification: A Comparative Study between ChatGPT and a Dedicated Model for This Task
%A Kelious, Abdelhak
%A Constant, Mathieu
%A Coeur, Christophe
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kelious-etal-2024-complex-word
%X There are several works in natural language processing for identifying lexical complexity. This can be for various reasons, either for simplification, the selection of more suitable content, or for other specific tasks. Words can have multiple definitions and degrees of complexity depending on the context in which they appear. One solution being investigated is lexical complexity prediction, where computational methods are used to evaluate the difficulty of vocabulary for language learners and offer personalized assistance. In this work, we explore deep learning methods to assess the complexity of a word based on its context. Specifically, we investigate how to use pre-trained language models to encode both the sentence and the target word, and then fine-tune them by combining them with additional frequency-based features. Our approach achieved superior results compared to the best systems in SemEval-2021 (Shardlow et al., 2021), as demonstrated by an R2 score of 0.65. Finally, we carry out a comparative study with ChatGPT to assess its potential for predicting lexical complexity, to see whether prompt engineering can be an alternative to this task, we will discuss the advantages and limitations of ChatGPT.
%U https://aclanthology.org/2024.lrec-main.323
%P 3645-3653
Markdown (Informal)
[Complex Word Identification: A Comparative Study between ChatGPT and a Dedicated Model for This Task](https://aclanthology.org/2024.lrec-main.323) (Kelious et al., LREC-COLING 2024)
ACL