@inproceedings{zhestiankin-ponomareva-2021-zhestyatsky,
title = "Zhestyatsky at {S}em{E}val-2021 Task 2: {R}e{LU} over Cosine Similarity for {BERT} Fine-tuning",
author = "Zhestiankin, Boris and
Ponomareva, Maria",
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-1.17",
doi = "10.18653/v1/2021.semeval-1.17",
pages = "163--168",
abstract = "This paper presents our contribution to SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). Our experiments cover English (EN-EN) sub-track from the multilingual setting of the task. We experiment with several pre-trained language models and investigate an impact of different top-layers on fine-tuning. We find the combination of Cosine Similarity and ReLU activation leading to the most effective fine-tuning procedure. Our best model results in accuracy 92.7{\%}, which is the fourth-best score in EN-EN sub-track.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhestiankin-ponomareva-2021-zhestyatsky">
<titleInfo>
<title>Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Zhestiankin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Ponomareva</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 our contribution to SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). Our experiments cover English (EN-EN) sub-track from the multilingual setting of the task. We experiment with several pre-trained language models and investigate an impact of different top-layers on fine-tuning. We find the combination of Cosine Similarity and ReLU activation leading to the most effective fine-tuning procedure. Our best model results in accuracy 92.7%, which is the fourth-best score in EN-EN sub-track.</abstract>
<identifier type="citekey">zhestiankin-ponomareva-2021-zhestyatsky</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.17</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.17</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>163</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning
%A Zhestiankin, Boris
%A Ponomareva, Maria
%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 zhestiankin-ponomareva-2021-zhestyatsky
%X This paper presents our contribution to SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). Our experiments cover English (EN-EN) sub-track from the multilingual setting of the task. We experiment with several pre-trained language models and investigate an impact of different top-layers on fine-tuning. We find the combination of Cosine Similarity and ReLU activation leading to the most effective fine-tuning procedure. Our best model results in accuracy 92.7%, which is the fourth-best score in EN-EN sub-track.
%R 10.18653/v1/2021.semeval-1.17
%U https://aclanthology.org/2021.semeval-1.17
%U https://doi.org/10.18653/v1/2021.semeval-1.17
%P 163-168
Markdown (Informal)
[Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning](https://aclanthology.org/2021.semeval-1.17) (Zhestiankin & Ponomareva, SemEval 2021)
ACL