This course starts with the basics of text processing including basic pre-processing, spelling correction, language modeling, Part-of-Speech tagging, Constituency and Dependency Parsing, Lexical Semantics, distributional Semantics and topic models. Finally, the course also covers some of the most interesting applications of text mining such as entity linking, relation extraction, text summarization, text classification, sentiment analysis and opinion mining.Pre-requisites Basic knowledge of probabilities for the lectures and python for programming assignmentIndustries Applicable Microsoft Research, Google, Adobe, Xerox, Flipkart, Amazon
Overview
Syllabus
Week 1: Introduction and Basic Text ProcessingWeek 2: Spelling Correction, Language ModelingWeek 3: Advanced smoothing for language modeling, POS taggingWeek 4: Models for Sequential tagging – MaxEnt, CRFWeek 5: Syntax – Constituency ParsingWeek 6: Dependency ParsingWeek 7: Distributional SemanticsWeek 8: Lexical SemanticsWeek 9: Topic ModelsWeek 10: Entity Linking, Information ExtractionWeek 11: Text Summarization, Text ClassificationWeek 12: Sentiment Analysis and Opinion Mining
