Mastering Text Classification: Cutting-Edge NLP Techniques

by Mourad Abbas (Editor)

Overview

This book provides cutting-edge natural language processing (NLP) techniques to unlock the power of text data. It presents advanced methods for various text classification tasks, like discourse relation classification, classification in large taxonomies, and leveraging disagreement between annotators for text classification.

This book equips readers whether they are researchers or professionals, looking to apply NLP in real-world settings, with the latest advancements, and gives them the opportunity to explore techniques to handle limited data, and harness the power of pre-trained language models like BERT. By the end, readers will be equipped to tackle specific text classification challenges and advance the field of NLP.

Product Details

ISBN-13:	9783031936128
Publisher:	Springer-Verlag New York, LLC
Publication date:	11/12/2025
Sold by:	Barnes & Noble
Format:	eBook
Pages:	142
File size:	9 MB

About the Author

Dr. Mourad Abbas is research director at the High Council of Arabic, specializing in the dynamic field of natural language processing with a primary focus on the Arabic language and its diverse dialects. With a passion for pushing the boundaries of NLP, Dr. Abbas' research interests span a wide range of crucial topics, including machine translation, speech recognition, language identification, natural language understanding, and the challenges faced by under-resourced languages. Throughout his career, Dr. Abbas has made many contributions to the academic community, having published over sixty impactful papers. He has also played an important role in editing the proceedings of the International Conference on Natural Language and Speech Processing, featured in prestigious platforms like Elsevier, ACL Anthology, and IEEExplore. Recognized as an expert in his field, Dr. Abbas is actively engaged in peer review activities for distinguished journals, such as Language Resources and Evaluation, and Digital Signal Processing, along with conferences like ICASSP, Interspeech, Coling, and NAACL-HLT.

Table of Contents

Introduction.- Handling Realistic Label Noise in BERT Text Classification.- Discourse Relations Classification and Cross-Framework Discourse Relation Classification through the Lens of Cognitive Dimensions: An Empirical Investigation.- Representation Learning for Hierarchical Classification of Entity Titles.- DAP-LeR-DAug: Techniques for enhanced Online Sexism Detection.- Automatic Detection of Generalized Patterns of Vossian Antonomasia.- Exploring BERT Models for Part-of-Speech Tagging in the Algerian Dialect.- Deep Learning-Based Claim Matching with Multiple Negatives Training.- A Neural Network Approach to Ellipsis Detection in Ancient Greek.- Conclusion.