@inproceedings{smolenska-etal-2021-clulex,
title = "{CLULEX} at {S}em{E}val-2021 Task 1: A Simple System Goes a Long Way",
author = {Smolenska, Greta and
Kolb, Peter and
Tang, Sinan and
Bitinis, Mironas and
Hern{\'a}ndez, H{\'e}ctor and
Askl{\"o}v, Elin},
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-1.81",
doi = "10.18653/v1/2021.semeval-1.81",
pages = "632--639",
abstract = "This paper presents the system we submitted to the first Lexical Complexity Prediction (LCP) Shared Task 2021. The Shared Task provides participants with a new English dataset that includes context of the target word. We participate in the single-word complexity prediction sub-task and focus on feature engineering. Our best system is trained on linguistic features and word embeddings (Pearson{'}s score of 0.7942). We demonstrate, however, that a simpler feature set achieves comparable results and submit a model trained on 36 linguistic features (Pearson{'}s score of 0.7925).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="smolenska-etal-2021-clulex">
<titleInfo>
<title>CLULEX at SemEval-2021 Task 1: A Simple System Goes a Long Way</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greta</namePart>
<namePart type="family">Smolenska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Kolb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sinan</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mironas</namePart>
<namePart type="family">Bitinis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Héctor</namePart>
<namePart type="family">Hernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elin</namePart>
<namePart type="family">Asklöv</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 paper presents the system we submitted to the first Lexical Complexity Prediction (LCP) Shared Task 2021. The Shared Task provides participants with a new English dataset that includes context of the target word. We participate in the single-word complexity prediction sub-task and focus on feature engineering. Our best system is trained on linguistic features and word embeddings (Pearson’s score of 0.7942). We demonstrate, however, that a simpler feature set achieves comparable results and submit a model trained on 36 linguistic features (Pearson’s score of 0.7925).</abstract>
<identifier type="citekey">smolenska-etal-2021-clulex</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.81</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.81</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>632</start>
<end>639</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLULEX at SemEval-2021 Task 1: A Simple System Goes a Long Way
%A Smolenska, Greta
%A Kolb, Peter
%A Tang, Sinan
%A Bitinis, Mironas
%A Hernández, Héctor
%A Asklöv, Elin
%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 smolenska-etal-2021-clulex
%X This paper presents the system we submitted to the first Lexical Complexity Prediction (LCP) Shared Task 2021. The Shared Task provides participants with a new English dataset that includes context of the target word. We participate in the single-word complexity prediction sub-task and focus on feature engineering. Our best system is trained on linguistic features and word embeddings (Pearson’s score of 0.7942). We demonstrate, however, that a simpler feature set achieves comparable results and submit a model trained on 36 linguistic features (Pearson’s score of 0.7925).
%R 10.18653/v1/2021.semeval-1.81
%U https://aclanthology.org/2021.semeval-1.81
%U https://doi.org/10.18653/v1/2021.semeval-1.81
%P 632-639
Markdown (Informal)
[CLULEX at SemEval-2021 Task 1: A Simple System Goes a Long Way](https://aclanthology.org/2021.semeval-1.81) (Smolenska et al., SemEval 2021)
ACL
- Greta Smolenska, Peter Kolb, Sinan Tang, Mironas Bitinis, Héctor Hernández, and Elin Asklöv. 2021. CLULEX at SemEval-2021 Task 1: A Simple System Goes a Long Way. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 632–639, Online. Association for Computational Linguistics.