Natural language processing
Graduate · CS / Programming
Syllabus focus
Standard syllabus · STEM / applied
Pricing
Graduate-level rates are set on consultation. See the pricing page for K–12 and undergraduate rates.
Topics typically covered
Standard syllabus
Classical NLP
- Tokenization, morphology, and n-gram language models
- Part-of-speech tagging and HMMs (intro)
- Context-free parsing and dependency parsing (intro)
- Word embeddings: Word2Vec, GloVe
- Information retrieval and TF-IDF baselines
Neural NLP
- Recurrent networks for sequence labeling
- Attention mechanisms and Transformer architecture
- Pretrained language models (BERT, GPT family survey)
- Fine-tuning vs prompting paradigms
- Evaluation metrics: perplexity, BLEU, ROUGE (intro)
STEM / applied
Applications and systems
- Machine translation pipelines
- Question answering and retrieval-augmented generation (intro)
- Sentiment analysis and text classification projects
- Efficient inference and model compression (intro)
- Multilingual and low-resource NLP challenges
Ethics and deployment
- Bias and toxicity in language models
- Privacy and memorization in LMs
- Human-in-the-loop annotation workflows
- Serving NLP models in production APIs
- Research project: replicate a baseline paper
Notes
Fast-moving field; syllabus may emphasize transformers and LLMs over classical parsing.