A survey of methods for addressing class imbalance in deep-learning based natural language processing

  • Many natural language processing (NLP) tasks are naturally imbalanced, as some target categories occur much more frequently than others in the real world. In such scenarios, current NLP models tend to perform poorly on less frequent classes. Addressing class imbalance in NLP is an active research topic, yet, finding a good approach for a particular task and imbalance scenario is difficult. In this survey, the first overview on class imbalance in deep-learning based NLP, we first discuss various types of controlled and real-world class imbalance. Our survey then covers approaches that have been explicitly proposed for class-imbalanced NLP tasks or, originating in the computer vision community, have been evaluated on them. We organize the methods by whether they are based on sampling, data augmentation, choice of loss function, staged learning, or model design. Finally, we discuss open problems and how to move forward.

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Sophie Henning, William Beluch, Alexander Fraser, Annemarie FriedrichORCiDGND
URN:urn:nbn:de:bvb:384-opus4-1055612
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/105561
ISBN:978-1-959429-44-9OPAC
Parent Title (English):Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), May 2-6, 2023, Dubrovnik, Croatia
Publisher:Association for Computational Linguistics (ACL)
Place of publication:Stroudsburg, PA
Editor:Andreas Vlachos, Isabelle Augenstein
Type:Conference Proceeding
Language:English
Year of first Publication:2023
Publishing Institution:Universität Augsburg
Release Date:2023/07/10
First Page:523
Last Page:540
DOI:https://doi.org/10.18653/v1/2023.eacl-main.38
Institutes:Fakultät für Angewandte Informatik
Fakultät für Angewandte Informatik / Institut für Informatik
Fakultät für Angewandte Informatik / Institut für Informatik / Professur für Sprachverstehen mit der Anwendung Digital Humanities
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):CC-BY 4.0: Creative Commons: Namensnennung (mit Print on Demand)

OPUS4 Logo