LING 3300 - Computers and Language

This class familiarizes students with tools (e.g., regular expressions, NLTK) used to find, retrieve, identify, tag, manipulate and analyze data from primary/in-the-field sources and established corpora. Students are introduced to ideas fundamental to Natural Language Processing, including Finite State Automata, parsing techniques, token identification, and the incorporation of statistical information for automated token tagging and identification.