Statistical Natural Language Processing

4 credits

Diving deep to the classical NLP pipeline: tokenization, stemming, lemmatization, part-of-speech tagging, named entity recognition, parsing, and machine translation. Finite-state transducer, context-free grammar, hidden Markov models (HMM), and conditional random fields (CRF) will be covered in detail. Prerequisites: none. Restricted to DSC-MS-001 and DSC-PhD-001 students.