Text Classification Task
Text classification, a core natural language processing task, aims to automatically categorize text into predefined categories. Current research emphasizes improving accuracy and efficiency, particularly in low-resource settings and with imbalanced datasets, exploring model architectures like transformers (e.g., BERT), graph neural networks, and support vector machines (SVMs), along with techniques such as data augmentation and active learning. These advancements have significant implications for various applications, including legal text analysis, sentiment analysis, and fraud detection, by enabling more accurate and efficient automated text processing.
Papers
Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Tasks
Mateusz Baran, Joanna Baran, Mateusz Wójcik, Maciej Zięba, Adam Gonczarek
Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models
Lautaro Estienne, Luciana Ferrer, Matías Vera, Pablo Piantanida