@inproceedings{bani-yaseen-etal-2021-just,
title = "{JUST}-{BLUE} at {S}em{E}val-2021 Task 1: Predicting Lexical Complexity using {BERT} and {R}o{BERT}a Pre-trained Language Models",
author = "Bani Yaseen, Tuqa and
Ismail, Qusai and
Al-Omari, Sarah and
Al-Sobh, Eslam and
Abdullah, Malak",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.85",
doi = "10.18653/v1/2021.semeval-1.85",
pages = "661--666",
abstract = "Predicting the complexity level of a word or a phrase is considered a challenging task. It is even recognized as a crucial step in numerous NLP applications, such as text rearrangements and text simplification. Early research treated the task as a binary classification task, where the systems anticipated the existence of a word{'}s complexity (complex versus uncomplicated). Other studies had been designed to assess the level of word complexity using regression models or multi-labeling classification models. Deep learning models show a significant improvement over machine learning models with the rise of transfer learning and pre-trained language models. This paper presents our approach that won the first rank in the SemEval-task1 (sub stask1). We have calculated the degree of word complexity from 0-1 within a text. We have been ranked first place in the competition using the pre-trained language models Bert and RoBERTa, with a Pearson correlation score of 0.788.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bani-yaseen-etal-2021-just">
<titleInfo>
<title>JUST-BLUE at SemEval-2021 Task 1: Predicting Lexical Complexity using BERT and RoBERTa Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuqa</namePart>
<namePart type="family">Bani Yaseen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qusai</namePart>
<namePart type="family">Ismail</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Al-Omari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eslam</namePart>
<namePart type="family">Al-Sobh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malak</namePart>
<namePart type="family">Abdullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Predicting the complexity level of a word or a phrase is considered a challenging task. It is even recognized as a crucial step in numerous NLP applications, such as text rearrangements and text simplification. Early research treated the task as a binary classification task, where the systems anticipated the existence of a word’s complexity (complex versus uncomplicated). Other studies had been designed to assess the level of word complexity using regression models or multi-labeling classification models. Deep learning models show a significant improvement over machine learning models with the rise of transfer learning and pre-trained language models. This paper presents our approach that won the first rank in the SemEval-task1 (sub stask1). We have calculated the degree of word complexity from 0-1 within a text. We have been ranked first place in the competition using the pre-trained language models Bert and RoBERTa, with a Pearson correlation score of 0.788.</abstract>
<identifier type="citekey">bani-yaseen-etal-2021-just</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.85</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.85</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>661</start>
<end>666</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JUST-BLUE at SemEval-2021 Task 1: Predicting Lexical Complexity using BERT and RoBERTa Pre-trained Language Models
%A Bani Yaseen, Tuqa
%A Ismail, Qusai
%A Al-Omari, Sarah
%A Al-Sobh, Eslam
%A Abdullah, Malak
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F bani-yaseen-etal-2021-just
%X Predicting the complexity level of a word or a phrase is considered a challenging task. It is even recognized as a crucial step in numerous NLP applications, such as text rearrangements and text simplification. Early research treated the task as a binary classification task, where the systems anticipated the existence of a word’s complexity (complex versus uncomplicated). Other studies had been designed to assess the level of word complexity using regression models or multi-labeling classification models. Deep learning models show a significant improvement over machine learning models with the rise of transfer learning and pre-trained language models. This paper presents our approach that won the first rank in the SemEval-task1 (sub stask1). We have calculated the degree of word complexity from 0-1 within a text. We have been ranked first place in the competition using the pre-trained language models Bert and RoBERTa, with a Pearson correlation score of 0.788.
%R 10.18653/v1/2021.semeval-1.85
%U https://aclanthology.org/2021.semeval-1.85
%U https://doi.org/10.18653/v1/2021.semeval-1.85
%P 661-666
Markdown (Informal)
[JUST-BLUE at SemEval-2021 Task 1: Predicting Lexical Complexity using BERT and RoBERTa Pre-trained Language Models](https://aclanthology.org/2021.semeval-1.85) (Bani Yaseen et al., SemEval 2021)
ACL