NLP-ICTS6361-2023

NLP-ICTS6361-2023

Natural Language Processing Course

1. Introduction to Natural Language Processing

• Overview of the field of NLP and its applications
• Understanding the challenges and limitations of NLP

2. Fundamentals of NLP

• Overview of the linguistic and computational foundations of NLP
• Key NLP tasks, including tokenization, stemming, and stopword removal

3. Text Representation

• Techniques for representing text data, including bag of words, TF-IDF, and word embeddings
• Overview of vector space models and semantic representations

4. NLP Tasks and Applications

• Overview of common NLP tasks, including sentiment analysis, named entity recognition, and machine translation

5. Deep Learning for NLP

• Overview of deep learning approaches for NLP
• Understanding recurrent neural networks (RNNs), convolutional neural networks (CNNs), and transformers

6. Advanced NLP Techniques

• Overview of advanced NLP techniques, including active learning, transfer learning, and unsupervised NLP
• Understanding recent developments in NLP, such as contextual representation models

7. NLP in Practice

• Best practices for NLP model selection and evaluation
• Overview of NLP tools and libraries, including NLTK, spaCy, and PyTorch

Evaluation:

• Selected Papers Presentation 30
• NLP Project 30
• Final Exam 40

Textbooks

• Speech and Language Processing by Dan Jurafsky and James H. Martin.
• Jacob Eisenstein. Natural Language Processing
• Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning
• Lewis Tunstall, Leandro von Werra, and Thomas Wolf. Natural Language Processing with Transformers

References

• Speech and Language Processing by Dan Jurafsky and James H. Martin.
• Stanford NLP course materials
• DNN cheatsheet

Python Libraries for NLP

• Natural Language Processing with Python
• spaCy 101: Everything you need to know

NLP Papers review

• NLP Progress
• Arabic NLP Survey Papers Repository

Arabic Corpora

• ARABIC NLP DATA CATALOGUE