Introduction to Natural Language Processing

Objectives: The main objective of this course is to make students understand the basic concepts and techniques of natural language processing. Students will have a clear and broad understanding of natural language processing upon completion of this course. Students will understand the design and implementation of techniques used in natural language processing. Hands-on experience on practical assignments based on application of NLP will help undergraduate students to improve their programming skills.

Contents: What is language processing? Zipf's law, collocations, elementary probability theory, essential information theory, corpora, natural language and formal language: regular expressions and finite state automata, regular expressions in NLP, word tokenization, word normalization and stemming, morphology, sentence segmentation, string edit distance and alignment, introduction to information retrieval, evaluation of information retrieval, text clustering and classification, sentiment analysis.