CSC464 Deep Learning for Natural Language Processing

[3–0, 3 cr.]

Understanding complex language has wide applications in web search, advertisement, customer service, automatic translation, chat bot engineering, etc. Many different machine learning techniques are at the heart of natural language processing (NLP) applications. Recently, Deep Learning (DL) approaches have obtained very high performance across many different NLP tasks. This course covers such approaches. Students will build their own neural network model and apply it to a large scale NLP problem. From the model side, the following topics will be covered:  word vector representations, window-based neural networks, recurrent neural networks, long-short-term-memory models, recursive neural networks, convolutional neural networks. From the NLP side, the course covers the following topics: syntax parsing, vector space modeling, dimensionality reduction, speech tagging, text classification, and sentiment analysis. 

Prerequisite: CSC310 Algorithms and Data Structures

Note: This course has not been taught since Fall 2021 and will not be taught during the academic year 20234-2025.