@inproceedings{north-etal-2022-evaluation,
title = "An Evaluation of Binary Comparative Lexical Complexity Models",
author = "North, Kai and
Zampieri, Marcos and
Shardlow, Matthew",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.bea-1.24",
doi = "10.18653/v1/2022.bea-1.24",
pages = "197--203",
abstract = "Identifying complex words in texts is an important first step in text simplification (TS) systems. In this paper, we investigate the performance of binary comparative Lexical Complexity Prediction (LCP) models applied to a popular benchmark dataset {---} the CompLex 2.0 dataset used in SemEval-2021 Task 1. With the data from CompLex 2.0, we create a new dataset contain 1,940 sentences referred to as CompLex-BC. Using CompLex-BC, we train multiple models to differentiate which of two target words is more or less complex in the same sentence. A linear SVM model achieved the best performance in our experiments with an F1-score of 0.86.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="north-etal-2022-evaluation">
<titleInfo>
<title>An Evaluation of Binary Comparative Lexical Complexity Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying complex words in texts is an important first step in text simplification (TS) systems. In this paper, we investigate the performance of binary comparative Lexical Complexity Prediction (LCP) models applied to a popular benchmark dataset — the CompLex 2.0 dataset used in SemEval-2021 Task 1. With the data from CompLex 2.0, we create a new dataset contain 1,940 sentences referred to as CompLex-BC. Using CompLex-BC, we train multiple models to differentiate which of two target words is more or less complex in the same sentence. A linear SVM model achieved the best performance in our experiments with an F1-score of 0.86.</abstract>
<identifier type="citekey">north-etal-2022-evaluation</identifier>
<identifier type="doi">10.18653/v1/2022.bea-1.24</identifier>
<location>
<url>https://aclanthology.org/2022.bea-1.24</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>197</start>
<end>203</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Evaluation of Binary Comparative Lexical Complexity Models
%A North, Kai
%A Zampieri, Marcos
%A Shardlow, Matthew
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F north-etal-2022-evaluation
%X Identifying complex words in texts is an important first step in text simplification (TS) systems. In this paper, we investigate the performance of binary comparative Lexical Complexity Prediction (LCP) models applied to a popular benchmark dataset — the CompLex 2.0 dataset used in SemEval-2021 Task 1. With the data from CompLex 2.0, we create a new dataset contain 1,940 sentences referred to as CompLex-BC. Using CompLex-BC, we train multiple models to differentiate which of two target words is more or less complex in the same sentence. A linear SVM model achieved the best performance in our experiments with an F1-score of 0.86.
%R 10.18653/v1/2022.bea-1.24
%U https://aclanthology.org/2022.bea-1.24
%U https://doi.org/10.18653/v1/2022.bea-1.24
%P 197-203
Markdown (Informal)
[An Evaluation of Binary Comparative Lexical Complexity Models](https://aclanthology.org/2022.bea-1.24) (North et al., BEA 2022)
ACL
- Kai North, Marcos Zampieri, and Matthew Shardlow. 2022. An Evaluation of Binary Comparative Lexical Complexity Models. In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022), pages 197–203, Seattle, Washington. Association for Computational Linguistics.