Natural language processing

• Titel: Natural language processing
• Titelzusatz: probability models in Python
• Institutionen: Lazy Programmer (Firm), [MitwirkendeR]
• Institutionen: Packt Publishing, [Verlag]
• Ausgabe: [First edition].
• Verlagsort: [Birmingham, United Kingdom]
• Verlag: Packt Publishing
• E-Jahr: 2024
• Jahr: [2024]
• Umfang: 1 online resource (1 video file (5 hr., 12 min.))
• Illustrationen: sound, color.
• Fussnoten: Online resource; title from title details screen (O’Reilly, viewed July 1, 2024)
• ISBN: 978-1-83620-185-4
• ISBN: 1-83620-185-0
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Python (Langage de programmation)
• Sach-SW: Traitement automatique des langues naturelles
• Sach-SW: Instructional films
• Sach-SW: Nonfiction films
• Sach-SW: Internet videos
• Sach-SW: Films de formation
• Sach-SW: Films autres que de fiction
• Sach-SW: Vidéos sur Internet
• K10plus-PPN: 1899109110
• K10plus-PPN:
  Universitätsbibliothek
• Lokale URL UB: Zum Volltext
• Lokale URL UB: Bibliothek der Medizinischen Fakultät Mannheim der Universität Heidelberg
• Bibliothek/Idn: UW / m4568072360
• Lokale URL Inst.: Zum Volltext

Abstract

Beginning with an introduction and course outline, students are offered a special offer to kickstart their learning journey in this course. Initial sections guide you through the setup process and provide the necessary code resources. The course emphasizes strategies for success, ensuring learners are well-prepared from the start. The course delves into spam detection, beginning with a problem description and intuition behind Naive Bayes. Participants engage in exercises and learn to address class imbalance while evaluating models using ROC, AUC, and F1 scores. Practical implementation in Python solidifies understanding. Following this, the course transitions to sentiment analysis, covering problem description, logistic regression, and training. Exercises and Python-based projects enable learners to apply concepts effectively. Text summarization is thoroughly explored with sections on vector-based methods and TextRank, from basic to advanced levels. Practical Python sessions ensure learners can implement these techniques. The course culminates with topic modeling, introducing LDA and NMF methods, complemented by Python coding exercises. A deep dive into Latent Semantic Analysis and applying SVD in NLP wraps up the curriculum, ensuring a well-rounded expertise in NLP.