This course will cover a broad range of topics related to NLP, including basic text processing (such as tokenization, stemming), language modeling, morphology, syntax, dependency parsing, distributional and lexical Semantics, sense disambiguation, information extraction etc. We will also introduce underlying theory from probability, statistics, machine learning that are essential to understand fundamental algorithms in NLP such as language modeling, HMM etc. This course will end with more advanced topics in NLP such as stylometry analysis, sentiment analysis, named-entity disambiguation, machine translation etc. The term projects will provide opportunity to the students to get hands-on experience on designing different real-world NLP models.
To discuss and analyze advantages and disadvanatges of basic NLP models such as HMM, CRF, n-gram and Wordnet
Adapt and implement exisiting NLP models and study their performance with respect to different datasets
To leverage real-world datasets in order to build models for advanced problems