Standard

Development of Folklore Motif Classifier Using Limited Data. / Matveeva, Maria; Malykh, Valentin.

Communications in Computer and Information Science. Springer Science and Business Media Deutschland GmbH, 2022. p. 40-48 (Communications in Computer and Information Science; Vol. 1731 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Research › peer-review

Harvard

Matveeva, M & Malykh, V 2022, Development of Folklore Motif Classifier Using Limited Data. in Communications in Computer and Information Science. Communications in Computer and Information Science, vol. 1731 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 40-48. https://doi.org/10.1007/978-3-031-23372-2_4

APA

Matveeva, M., & Malykh, V. (2022). Development of Folklore Motif Classifier Using Limited Data. In Communications in Computer and Information Science (pp. 40-48). (Communications in Computer and Information Science; Vol. 1731 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-23372-2_4

Vancouver

Matveeva M, Malykh V. Development of Folklore Motif Classifier Using Limited Data. In Communications in Computer and Information Science. Springer Science and Business Media Deutschland GmbH. 2022. p. 40-48. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-23372-2_4

Author

Matveeva, Maria ; Malykh, Valentin. / Development of Folklore Motif Classifier Using Limited Data. Communications in Computer and Information Science. Springer Science and Business Media Deutschland GmbH, 2022. pp. 40-48 (Communications in Computer and Information Science).

BibTeX

@inbook{4ac6ce400cca4ecc894515689d03a484,
title = "Development of Folklore Motif Classifier Using Limited Data",
abstract = "The existence of mythological universals - common or similar folklore images and motifs in different cultures, makes it possible to catalog them and present them in the form of classifications. Attributing folklore texts to certain motifs is part of the work of folklorists, but at the moment only manual marking is possible. This paper proposes methods for developing a classifier of folklore motifs using the zero-shot approach, which makes it possible to train the classifier on a limited dataset, and also allows to predict the motif for any text, even if the text with such a motif was not present in the training set. Various ways of vectorizing texts and various models were tested. Evaluation of the results of the classifiers{\textquoteright} work allows us to assert that the developed classifier can correlate texts with motifs with sufficient accuracy.",
keywords = "Multi-label classification, Text classification, Zero-shot learning",
author = "Maria Matveeva and Valentin Malykh",
note = "Публикация для корректировки.",
year = "2022",
doi = "10.1007/978-3-031-23372-2_4",
language = "English",
isbn = "9783031233715",
series = "Communications in Computer and Information Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "40--48",
booktitle = "Communications in Computer and Information Science",
address = "Germany",

}

RIS

TY - CHAP

T1 - Development of Folklore Motif Classifier Using Limited Data

AU - Matveeva, Maria

AU - Malykh, Valentin

N1 - Публикация для корректировки.

PY - 2022

Y1 - 2022

N2 - The existence of mythological universals - common or similar folklore images and motifs in different cultures, makes it possible to catalog them and present them in the form of classifications. Attributing folklore texts to certain motifs is part of the work of folklorists, but at the moment only manual marking is possible. This paper proposes methods for developing a classifier of folklore motifs using the zero-shot approach, which makes it possible to train the classifier on a limited dataset, and also allows to predict the motif for any text, even if the text with such a motif was not present in the training set. Various ways of vectorizing texts and various models were tested. Evaluation of the results of the classifiers’ work allows us to assert that the developed classifier can correlate texts with motifs with sufficient accuracy.

AB - The existence of mythological universals - common or similar folklore images and motifs in different cultures, makes it possible to catalog them and present them in the form of classifications. Attributing folklore texts to certain motifs is part of the work of folklorists, but at the moment only manual marking is possible. This paper proposes methods for developing a classifier of folklore motifs using the zero-shot approach, which makes it possible to train the classifier on a limited dataset, and also allows to predict the motif for any text, even if the text with such a motif was not present in the training set. Various ways of vectorizing texts and various models were tested. Evaluation of the results of the classifiers’ work allows us to assert that the developed classifier can correlate texts with motifs with sufficient accuracy.

KW - Multi-label classification

KW - Text classification

KW - Zero-shot learning

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85148696505&origin=inward&txGid=79ba96c140cfa4c6c51d64c7622d1313

UR - https://www.mendeley.com/catalogue/1c834160-cbe4-3c00-8fb4-ff2e6f226cea/

U2 - 10.1007/978-3-031-23372-2_4

DO - 10.1007/978-3-031-23372-2_4

M3 - Chapter

SN - 9783031233715

T3 - Communications in Computer and Information Science

SP - 40

EP - 48

BT - Communications in Computer and Information Science

PB - Springer Science and Business Media Deutschland GmbH

ER -

ID: 55720230