@inproceedings{ortiz-zambrano-montejo-raez-2021-complex,
title = "Complex words identification using word-level features for {S}em{E}val-2020 Task 1",
author = "Ortiz-Zambrano, Jenny A. and
Montejo-R{\'a}ez, Arturo",
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-1.11",
doi = "10.18653/v1/2021.semeval-1.11",
pages = "126--129",
abstract = "This article describes a system to predict the complexity of words for the Lexical Complexity Prediction (LCP) shared task hosted at SemEval 2021 (Task 1) with a new annotated English dataset with a Likert scale. Located in the Lexical Semantics track, the task consisted of predicting the complexity value of the words in context. A machine learning approach was carried out based on the frequency of the words and several characteristics added at word level. Over these features, a supervised random forest regression algorithm was trained. Several runs were performed with different values to observe the performance of the algorithm. For the evaluation, our best results reported a M.A.E score of 0.07347, M.S.E. of 0.00938, and R.M.S.E. of 0.096871. Our experiments showed that, with a greater number of characteristics, the precision of the classification increases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ortiz-zambrano-montejo-raez-2021-complex">
<titleInfo>
<title>Complex words identification using word-level features for SemEval-2020 Task 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jenny</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Ortiz-Zambrano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Ráez</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>This article describes a system to predict the complexity of words for the Lexical Complexity Prediction (LCP) shared task hosted at SemEval 2021 (Task 1) with a new annotated English dataset with a Likert scale. Located in the Lexical Semantics track, the task consisted of predicting the complexity value of the words in context. A machine learning approach was carried out based on the frequency of the words and several characteristics added at word level. Over these features, a supervised random forest regression algorithm was trained. Several runs were performed with different values to observe the performance of the algorithm. For the evaluation, our best results reported a M.A.E score of 0.07347, M.S.E. of 0.00938, and R.M.S.E. of 0.096871. Our experiments showed that, with a greater number of characteristics, the precision of the classification increases.</abstract>
<identifier type="citekey">ortiz-zambrano-montejo-raez-2021-complex</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.11</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.11</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>126</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Complex words identification using word-level features for SemEval-2020 Task 1
%A Ortiz-Zambrano, Jenny A.
%A Montejo-Ráez, Arturo
%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 ortiz-zambrano-montejo-raez-2021-complex
%X This article describes a system to predict the complexity of words for the Lexical Complexity Prediction (LCP) shared task hosted at SemEval 2021 (Task 1) with a new annotated English dataset with a Likert scale. Located in the Lexical Semantics track, the task consisted of predicting the complexity value of the words in context. A machine learning approach was carried out based on the frequency of the words and several characteristics added at word level. Over these features, a supervised random forest regression algorithm was trained. Several runs were performed with different values to observe the performance of the algorithm. For the evaluation, our best results reported a M.A.E score of 0.07347, M.S.E. of 0.00938, and R.M.S.E. of 0.096871. Our experiments showed that, with a greater number of characteristics, the precision of the classification increases.
%R 10.18653/v1/2021.semeval-1.11
%U https://aclanthology.org/2021.semeval-1.11
%U https://doi.org/10.18653/v1/2021.semeval-1.11
%P 126-129
Markdown (Informal)
[Complex words identification using word-level features for SemEval-2020 Task 1](https://aclanthology.org/2021.semeval-1.11) (Ortiz-Zambrano & Montejo-Ráez, SemEval 2021)
ACL