CS 6390 - Information Extraction from Text

This course will study methods for extracting different types of information from unstructured natural language text. We will study algorithms to extract semantic concepts (e.g., name entities, semantic classes, semantic roles), factual information (e.g., event role fillers, event chains, factual relations), and subjective information (e.g., sentiment and opinion extraction). The course will include methods for extracting information from text corpora as well as the Web, and will discuss applications for both broad-coverage and domain-specific information extraction.