A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing

Henning, Sophie; Beluch, William; Fraser, Alexander und Friedrich, Annemarie (2023): A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing. 17th Conference of the European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia, 2023.05.02-06. Vlachos, Andreas und Augenstein, Isabelle (eds.) : In: 17th Conference of the European Chapter of the Association for Computational Linguistics - proceedings of the conference : May 2-6, 2023 : EACL 2023, Stroudsburg, PA: Association for Computational Linguistics (ACL). pp. 523-540

Abstract

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.

• Item Type: Conference or Workshop Item (Paper)
• Research Centers: Center for Information and Language Processing (CIS)
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science; 400 Language > 410 Linguistics
• ISBN: 978-1-959429-44-9
• Place of Publication: Stroudsburg, PA
• Language: English