Standard

Prepositional Phrase Classification in Russian with Transformer Models. / Belyi, A.; Boitsova, D.; Botvineva, E.

Internet and Modern Society. Human-Computer Communication (IMS 2024). Springer Nature, 2026. стр. 130-139 (Communications in Computer and Information Science; Том 2534 CCIS).

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование

Harvard

Belyi, A, Boitsova, D & Botvineva, E 2026, Prepositional Phrase Classification in Russian with Transformer Models. в Internet and Modern Society. Human-Computer Communication (IMS 2024). Communications in Computer and Information Science, Том. 2534 CCIS, Springer Nature, стр. 130-139, XXVII Международная объединенная научная конференция «Интернет и современное общество», Санкт-Петербург, Российская Федерация, 24/06/24. https://doi.org/10.1007/978-3-031-96177-9_11

APA

Belyi, A., Boitsova, D., & Botvineva, E. (2026). Prepositional Phrase Classification in Russian with Transformer Models. в Internet and Modern Society. Human-Computer Communication (IMS 2024) (стр. 130-139). (Communications in Computer and Information Science; Том 2534 CCIS). Springer Nature. https://doi.org/10.1007/978-3-031-96177-9_11

Vancouver

Belyi A, Boitsova D, Botvineva E. Prepositional Phrase Classification in Russian with Transformer Models. в Internet and Modern Society. Human-Computer Communication (IMS 2024). Springer Nature. 2026. стр. 130-139. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-031-96177-9_11

Author

Belyi, A. ; Boitsova, D. ; Botvineva, E. / Prepositional Phrase Classification in Russian with Transformer Models. Internet and Modern Society. Human-Computer Communication (IMS 2024). Springer Nature, 2026. стр. 130-139 (Communications in Computer and Information Science).

BibTeX

@inproceedings{9d11bf9d54854e33b12a3c4788eafd9a,
title = "Prepositional Phrase Classification in Russian with Transformer Models",
abstract = "In this paper we discuss the task of prepositional phrase classification in the Russian annotated corpus of prepositional phrases. As previous research has shown, differentiation of highly confused classes, namely THEME and OBJECT classes, remains a problem waiting for the computational solution. Since simple classifier architecture demonstrates significant performance on these classes, we propose a tree-based classifier architecture to improve performance on the whole and these classes specifically. This architecture consists of a main classifier validating its decisions concerning troublesome classes with another supporting classifier, trained to differentiate between the classes causing performance dropdown. We experiment with various types of classifiers inside of our architecture and various embedding models for the Russian language, which we use for encoding the dataset. The best result that we managed to achieve is an overall F1-score of 0.76 on the validation set using the classifier trained with DeepPavlov/rubert-base-cased model and SVM (Support Vector Machines) classifiers. {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.",
keywords = "phrase embeddings, prepositional phrases, text classification, transformers, word sense disambiguation, Architecture, Classification (of information), Computational linguistics, Embeddings, Natural language processing systems, Text processing, Computational solutions, Performance, Phrase embedding, Prepositional phrase, Simple++, Text classification, Transformer, Transformer modeling, Word Sense Disambiguation, Support vector machines",
author = "A. Belyi and D. Boitsova and E. Botvineva",
note = "Export Date: 29 March 2026; Cited By: 0; Correspondence Address: D. Boitsova; Saint Petersburg State University, St. Petersburg, Russian Federation; email: st087202@student.spbu.ru; Conference name: 27th International Conference on Internet and Modern Society, IMS 2024; Conference date: 24 June 2024 through 26 June 2024; Conference code: 339649; null ; Conference date: 24-06-2024 Through 26-06-2024",
year = "2026",
doi = "10.1007/978-3-031-96177-9_11",
language = "Английский",
isbn = "9783031961762",
series = "Communications in Computer and Information Science",
publisher = "Springer Nature",
pages = "130--139",
booktitle = "Internet and Modern Society. Human-Computer Communication (IMS 2024)",
address = "Германия",
url = "https://ims.itmo.ru , https://ims.itmo.ru/, https://ims.itmo.ru",

}

RIS

TY - GEN

T1 - Prepositional Phrase Classification in Russian with Transformer Models

AU - Belyi, A.

AU - Boitsova, D.

AU - Botvineva, E.

N1 - Conference code: XXVII

PY - 2026

Y1 - 2026

N2 - In this paper we discuss the task of prepositional phrase classification in the Russian annotated corpus of prepositional phrases. As previous research has shown, differentiation of highly confused classes, namely THEME and OBJECT classes, remains a problem waiting for the computational solution. Since simple classifier architecture demonstrates significant performance on these classes, we propose a tree-based classifier architecture to improve performance on the whole and these classes specifically. This architecture consists of a main classifier validating its decisions concerning troublesome classes with another supporting classifier, trained to differentiate between the classes causing performance dropdown. We experiment with various types of classifiers inside of our architecture and various embedding models for the Russian language, which we use for encoding the dataset. The best result that we managed to achieve is an overall F1-score of 0.76 on the validation set using the classifier trained with DeepPavlov/rubert-base-cased model and SVM (Support Vector Machines) classifiers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

AB - In this paper we discuss the task of prepositional phrase classification in the Russian annotated corpus of prepositional phrases. As previous research has shown, differentiation of highly confused classes, namely THEME and OBJECT classes, remains a problem waiting for the computational solution. Since simple classifier architecture demonstrates significant performance on these classes, we propose a tree-based classifier architecture to improve performance on the whole and these classes specifically. This architecture consists of a main classifier validating its decisions concerning troublesome classes with another supporting classifier, trained to differentiate between the classes causing performance dropdown. We experiment with various types of classifiers inside of our architecture and various embedding models for the Russian language, which we use for encoding the dataset. The best result that we managed to achieve is an overall F1-score of 0.76 on the validation set using the classifier trained with DeepPavlov/rubert-base-cased model and SVM (Support Vector Machines) classifiers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

KW - phrase embeddings

KW - prepositional phrases

KW - text classification

KW - transformers

KW - word sense disambiguation

KW - Architecture

KW - Classification (of information)

KW - Computational linguistics

KW - Embeddings

KW - Natural language processing systems

KW - Text processing

KW - Computational solutions

KW - Performance

KW - Phrase embedding

KW - Prepositional phrase

KW - Simple++

KW - Text classification

KW - Transformer

KW - Transformer modeling

KW - Word Sense Disambiguation

KW - Support vector machines

UR - https://www.mendeley.com/catalogue/f4761c81-3361-3178-a630-e4a532e274d4/

U2 - 10.1007/978-3-031-96177-9_11

DO - 10.1007/978-3-031-96177-9_11

M3 - статья в сборнике материалов конференции

SN - 9783031961762

T3 - Communications in Computer and Information Science

SP - 130

EP - 139

BT - Internet and Modern Society. Human-Computer Communication (IMS 2024)

PB - Springer Nature

Y2 - 24 June 2024 through 26 June 2024

ER -

ID: 151442632