@inproceedings{rivas-rojas-alva-manchego-2021-iapucp,
title = "{IAPUCP} at {S}em{E}val-2021 Task 1: Stacking Fine-Tuned Transformers is Almost All You Need for Lexical Complexity Prediction",
author = "Rivas Rojas, Kervy and
Alva-Manchego, Fernando",
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-1.14",
doi = "10.18653/v1/2021.semeval-1.14",
pages = "144--149",
abstract = "This paper describes our submission to SemEval-2021 Task 1: predicting the complexity score for single words. Our model leverages standard morphosyntactic and frequency-based features that proved helpful for Complex Word Identification (a related task), and combines them with predictions made by Transformer-based pre-trained models that were fine-tuned on the Shared Task data. Our submission system stacks all previous models with a LightGBM at the top. One novelty of our approach is the use of multi-task learning for fine-tuning a pre-trained model for both Lexical Complexity Prediction and Word Sense Disambiguation. Our analysis shows that all independent models achieve a good performance in the task, but that stacking them obtains a Pearson correlation of 0.7704, merely 0.018 points behind the winning submission.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rivas-rojas-alva-manchego-2021-iapucp">
<titleInfo>
<title>IAPUCP at SemEval-2021 Task 1: Stacking Fine-Tuned Transformers is Almost All You Need for Lexical Complexity Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kervy</namePart>
<namePart type="family">Rivas Rojas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</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 describes our submission to SemEval-2021 Task 1: predicting the complexity score for single words. Our model leverages standard morphosyntactic and frequency-based features that proved helpful for Complex Word Identification (a related task), and combines them with predictions made by Transformer-based pre-trained models that were fine-tuned on the Shared Task data. Our submission system stacks all previous models with a LightGBM at the top. One novelty of our approach is the use of multi-task learning for fine-tuning a pre-trained model for both Lexical Complexity Prediction and Word Sense Disambiguation. Our analysis shows that all independent models achieve a good performance in the task, but that stacking them obtains a Pearson correlation of 0.7704, merely 0.018 points behind the winning submission.</abstract>
<identifier type="citekey">rivas-rojas-alva-manchego-2021-iapucp</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.14</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.14</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>144</start>
<end>149</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IAPUCP at SemEval-2021 Task 1: Stacking Fine-Tuned Transformers is Almost All You Need for Lexical Complexity Prediction
%A Rivas Rojas, Kervy
%A Alva-Manchego, Fernando
%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 rivas-rojas-alva-manchego-2021-iapucp
%X This paper describes our submission to SemEval-2021 Task 1: predicting the complexity score for single words. Our model leverages standard morphosyntactic and frequency-based features that proved helpful for Complex Word Identification (a related task), and combines them with predictions made by Transformer-based pre-trained models that were fine-tuned on the Shared Task data. Our submission system stacks all previous models with a LightGBM at the top. One novelty of our approach is the use of multi-task learning for fine-tuning a pre-trained model for both Lexical Complexity Prediction and Word Sense Disambiguation. Our analysis shows that all independent models achieve a good performance in the task, but that stacking them obtains a Pearson correlation of 0.7704, merely 0.018 points behind the winning submission.
%R 10.18653/v1/2021.semeval-1.14
%U https://aclanthology.org/2021.semeval-1.14
%U https://doi.org/10.18653/v1/2021.semeval-1.14
%P 144-149
Markdown (Informal)
[IAPUCP at SemEval-2021 Task 1: Stacking Fine-Tuned Transformers is Almost All You Need for Lexical Complexity Prediction](https://aclanthology.org/2021.semeval-1.14) (Rivas Rojas & Alva-Manchego, SemEval 2021)
ACL