Standard
MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection. / Kotyushev, Mikhail; Glazkova, Anna; Morozov, Dmitry.
SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop. ред. / Alexis Palmer; Nathan Schneider; Natalie Schluter; Guy Emerson; Aurelie Herbelot; Xiaodan Zhu. Association for Computational Linguistics (ACL), 2021. стр. 913-918 (SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop).
Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
Harvard
Kotyushev, M, Glazkova, A
& Morozov, D 2021,
MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection. в A Palmer, N Schneider, N Schluter, G Emerson, A Herbelot & X Zhu (ред.),
SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop. SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop, Association for Computational Linguistics (ACL), стр. 913-918, 15th International Workshop on Semantic Evaluation, SemEval 2021, Virtual, Bangkok, Таиланд,
05.08.2021.
APA
Kotyushev, M., Glazkova, A.
, & Morozov, D. (2021).
MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection. в A. Palmer, N. Schneider, N. Schluter, G. Emerson, A. Herbelot, & X. Zhu (Ред.),
SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop (стр. 913-918). (SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop). Association for Computational Linguistics (ACL).
Vancouver
Kotyushev M, Glazkova A
, Morozov D.
MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection. в Palmer A, Schneider N, Schluter N, Emerson G, Herbelot A, Zhu X, Редакторы, SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2021. стр. 913-918. (SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop).
Author
BibTeX
@inproceedings{2bc0ab7eeccb4fdb8bffabedce973f2f,
title = "MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection",
abstract = "This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language models using various ensemble techniques for toxic span identification and achieved sizable improvements over our baseline fine-tuned BERT models. Finally, our system obtained a F1-score of 67.55% on test data.",
author = "Mikhail Kotyushev and Anna Glazkova and Dmitry Morozov",
note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; 15th International Workshop on Semantic Evaluation, SemEval 2021 ; Conference date: 05-08-2021 Through 06-08-2021",
year = "2021",
language = "English",
isbn = "9781954085701",
series = "SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "913--918",
editor = "Alexis Palmer and Nathan Schneider and Natalie Schluter and Guy Emerson and Aurelie Herbelot and Xiaodan Zhu",
booktitle = "SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop",
}
RIS
TY - GEN
T1 - MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection
AU - Kotyushev, Mikhail
AU - Glazkova, Anna
AU - Morozov, Dmitry
N1 - Publisher Copyright:
© 2021 Association for Computational Linguistics.
PY - 2021
Y1 - 2021
N2 - This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language models using various ensemble techniques for toxic span identification and achieved sizable improvements over our baseline fine-tuned BERT models. Finally, our system obtained a F1-score of 67.55% on test data.
AB - This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language models using various ensemble techniques for toxic span identification and achieved sizable improvements over our baseline fine-tuned BERT models. Finally, our system obtained a F1-score of 67.55% on test data.
UR - http://www.scopus.com/inward/record.url?scp=85131403176&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85131403176
SN - 9781954085701
T3 - SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop
SP - 913
EP - 918
BT - SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop
A2 - Palmer, Alexis
A2 - Schneider, Nathan
A2 - Schluter, Natalie
A2 - Emerson, Guy
A2 - Herbelot, Aurelie
A2 - Zhu, Xiaodan
PB - Association for Computational Linguistics (ACL)
T2 - 15th International Workshop on Semantic Evaluation, SemEval 2021
Y2 - 5 August 2021 through 6 August 2021
ER -
