CS 682 - Language Processing and Knowledge Graphs

Prerequisites
CS 660 and CS 661

This course surveys the principal difficulties of working with written language data, the fundamental techniques that are used in processing natural language, and the core applications of NLP technology. Topics covered in the course include language modeling, text classification, labeling sequential data (tagging), parsing, information extraction, question answering, machine translation, and semantics. The dominant paradigm in contemporary NLP uses supervised machine learning to train models based on either probability theory or deep neural networks. Both approaches are studied.

The objective of language processing when working with complex technical texts is to be able to make sense of information in a mixed structured/unstructured format. Information models to approach formalized technical language processing are explored. This course covers advanced text processing and machine learning algorithms and techniques for working with knowledge graphs and text data. This includes a wide range of algorithms for neural networks, machine learning, graph processing, text processing, and information retrieval with a focus of gaining insights into the knowledge stored in data. This is an implementation-intensive research-oriented seminar, where a particular data science application will be developed by reading research publications and implementing a software prototype.

Course credits: 3