DATA 6100 - Natural Language Processing 3

DATA 6100 Natural Language Processing. (3) The course presents algorithms and techniques for processing, numeric encoding, and mining of human language expressions. This course introduces prominent text modeling and numeric encoding techniques, including bag-of-words, frequency-based features, lexicon-based models, and word embedding models. Topics of text analytics include text processing and normalization, text classification and clustering, sentiment analysis on social media, topic modeling and document summarization, graph-based mining of large document, deep learning of text sequence, and machine translation. This course shares concepts from linguistics, statistics, and computer science. Prerequisite(s): DATA 5050 and DATA 5100.