Back to Study Plans

35 Problems

Cracking NLP

Master natural language processing from tokenization to large language models. Build the skills for NLP-focused ML interviews.

13 Easy16 Medium6 Hard

Unlock the full study plan

Upgrade to Pro to access the full curriculum.

5 sections

Tokenization Text Normalization Regex Patterns for NLP Padding and Truncation Stemming vs Lemmatization Sentence Segmentation Edit Distance Vocabulary Building Subword Tokenization Text Preprocessing Quiz10 questions

Bag of Words Embedding Similarity TF-IDF N-gram Language Model Sentence Embeddings Word2Vec GloVe FastText Embeddings & Representations Quiz10 questions

Named Entity Recognition POS Tagging Greedy Sequence Tagging Text Classification Language Modeling Spell Correction Sequence Models Quiz10 questions

Masked Language Modeling Next Sentence Prediction Token Classification Span Extraction Beam Search Decoding Text Generation Sampling Transformers for NLP Quiz10 questions

Perplexity Computation Text Deduplication (MinHash)Evaluation Metrics (BLEU, ROUGE)Tokenizer Training Document Ranking Byte Pair Encoding Advanced NLP Quiz10 questions

Summary

Total35

Easy13

Medium16

Hard6

Progress0%

Quizzes0/5