This is a draft course description for CE-08: Data Mining taught in Spring 2022.

Course content

Introduction to NLP, linguistics and NLP tasks, Python libraries for NLP, Text preprocessing and N-grams, Softmax / MAXENT (sequence) classifiers, sequence classifiers for POS & NER, Deep learning based word representations & deep networks for NER, Recurrent networks and language modeling, Statistical machine translation, Machine translation: word alignment, parallel corpora, decoding, evaluation, Modern deep learning machine translation systems (phrase-based, syntactic), Syntax and parsing, co-reference resolution, Tree recursive neural networks for POS tagging, Computational semantics, Question answering, Text summarization, Dialogue systems