Intelligent systems and interfaces have become more of a reality than being part of a sci-fi movie. Natural Language Processing (NLP) is one of the integral part of such interfaces. Statistics and Machine Learning (ML) have been used extensively to solve several problems in NLP. This course aims to introduce basic concepts in NLP, and to discuss statistical and ML models to solve NLP tasks. The course will focus on very specific NLP tasks and corresponding models.
NLP Topics - Language Model, Sequence Tagging, PoS Tagging, NER, Vector Space Models, Distributional Semantics, Distributed Semantics/word embedding.
ML Topics - Markov Models, HMM, Log-Linear Models, MEMM, CRF, Neural Language Model, Neural Network, Representation Learning.
Class Location and Time Calendar
Location: Room 2101 (at Core 2, 1st Floor)
- Monday  5 - 5:55 PM
- Tuesday  4 - 4:55 PM
- Wednesday  3 - 3:55 PM
(names in alphabetical order)
Grading Policy (Tentative)
Syllabus and References
Background reading material will be made available before the respective lecture, if required.