Enhancing Arabic-text feature extraction utilizing label-semantic augmentation in few/zero-shot learning

• المؤلفون الرئيسيون: Basabain, Seham, Cambria, Erik, Alomar, Khalid, Hussain, Amir
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2023
• الموضوعات: Engineering::Computer science and engineering; Arabic Text Classification; Contextual Embeddings
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/172293
• المؤسسة: Nanyang Technological University

A growing amount of research use pre-trained language models to address few/zero-shot text classification problems. Most of these studies neglect the semantic information hidden implicitly beneath the natural language names of class labels and develop a meta learner from the input texts solely. In t...