Resources

These are resources from the class.

Slides [Updated for 2025]

Note: Slides are provided under Creative Commons 4.0 Share-Alike. You are encouraged to make comments on the slides so that they can be improved.

• Block 1: Introduction to NLP [Slides]
• Block 2: Modern NLP Approaches [Slides]
• Block 3: Data Science + NLP [Slides]

Block 1: Introduction to NLP

• NLP with sklearn URL
• NLP for hackers URL

Block 2: Modern NLP Approaches

• Hugging Face URL
• FastAI NLP URL

Block 3: Data Science + NLP

African Language NLP

• Masakhane African Machine Translation URL

Data Augmentation

• TextAugment Library URL

Datasets

Misinformation/Disinformation

• Credibility Corpus (Twitter, Web) in French and English
• Fake News Challenge
• Fake News (Kaggle)
• Hyperpartisan News Detection
• RumourEval

Hate Speech

• hatEval: Multilingual hate speech detection
• OffensEval: Offensive Language in Social Media
• HateSpeech Dataset

African Languages

• Masakhane Datasets

Other

• Real411
• Wluper Dataset Downloads
• AYLIEN COVID-19 News Dataset

Presentations/Readings from other Researchers

• “How to do good research, get it published in SIGKDD and get it cited!”, Eamonn Keogh, SIGKDD 2009 Tutorial. URL
• Heuristics for Scientific Writing (a Machine Learning Perspective) - Zachary C. Lipton URL
• Developing Language Annotation for Machine Learning Algorithms - Marie Meteer URL

Other Courses

• Natural Language Processing with Deep Learning - C Manning URL
• Ethical NLP - E Bender URL
• Computational Ethics for NLP - Y Tsvetkov, AW Black URL
• Advanced Computational Linguistics - G Hirst URL