Machine Learning and Text Correction
This course will provide an overview of the state-of-the-art Natural Language Processing (NLP) techniques, with a focus on methods used in the field of automated text correction. The problem of grammar and spelling correction has always attracted NLP researchers but has become especially popular in the last few years, as the amount of “noisy” data has increased dramatically. We will study modern computational approaches used in the processing of different types of non-standard data, including texts written by non-native writers, medical and clinical documents, and social media data.
This is a research-oriented course, intended to provide the students with knowledge of the state-of-the-art computational techniques used in the field of automated text correction, and to develop basic skills required for reading and understanding research papers in NLP. In the course of the project, the students will learn about modern methods in Machine Learning and Natural Language Processing and will work on a research project of their own.
The course will consist of lectures, readings, and presentations.
Readings will be assigned from published notes and research papers that will be made available online.
Background and prerequisites
The course is intended for graduate students who are interested in Machine Learning, Natural Language Processing, and related areas. Prior background in Machine Learning and Natural Language Processing is recommended, but not required.
The assessment will be based on class participation, research papers discussion and presentation, and the final project, which students present in class.