Program Overview

The first course in a series covering the core concepts and algorithms for the theory and practice of natural language processing (NLP), the creation of computer programs that can understand, generate, and learn natural language.
5 Credits
Quarter: Fall

This is the second course in a series covering the core concepts and algorithms for the theory and practice of natural language processing (NLP)—the creation of computer programs that can understand, generate, and learn natural language.
5 credits
Quarter: Winter

Third and final course in a series covering the core concepts and algorithms for the theory and practice of natural language processing (NLP)—the creation of computer programs that can understand, generate, and learn natural language.
5 credits
Quarter: Spring

This course covers a broad set of tools and core skills required for working with Natural Language Data. It covers core traditional machine learning methods such as classification methods using Naive Bayes, SVMs, Linear regression and Support Vector Regression, as well as the use of Pytorch and other programming frameworks commonly used in the field. It also includes methods used for collecting, merging, cleaning, structuring and analyzing the properties of large and heterogeneous datasets of natural language, in order to address questions and support applications relying on those data. It covers working with existing corpora as well as the challenges in collecting new corpora. 
5 credits
Quarter: Fall

Introduction to machine learning models and algorithms for natural language processing (NLP) including deep learning approaches. Targeted at professional master’s degree students, this course focuses on applications and current use of these methods in industry. Topics include: an introduction to standard neural network learning methods such as feed-forward neural networks; recurrent neural networks; convolutional neural networks; and encoder-decoder models with applications to natural language processing problems such as utterance classification and sequence tagging.
5 credits
Quarter: Fall

Introduces advanced machine learning models and algorithms for Natural Language Processing. Theoretical and intuitive understanding of NLP learning models will be discussed. Some hot topics such as robustness and explainability in ML for NLP will also be covered.
5 credits
Quarter: Winter

Weekly seminar course covering current research and advanced development in all areas of Natural Language Processing. The seminar is based on invited talks by guest speakers from industry research and advanced development working in the area of Natural Language Processing. Students attend talks given by speakers in a weekly seminar series and participate in group discussion. This class can be taken for Satisfactory/Unsatisfactory credit only.
2 credits: Must be taken twice
Quarter: Winter, Spring

{{ Link to Seminar}}

The first in a sequence of two Capstone courses providing hands-on practice of key NLP concepts and skills and experience working in a team project setting. The course provides students with tools for project management and teamwork. It also explores multiple possible projects, and methods for presenting projects, and investigates what makes a good project proposal, and how to evaluate and understand the strengths and weaknesses of project proposals.
5 credits
Quarter: Spring

This course is the second in a sequence of two Capstone courses providing hands-on practice of key NLP concepts and skills and experience working in a team project setting. This course will require students to work in small teams under the guidance of an industry or faculty mentor. In the first part of the quarter, each team will each create a substantial project proposal, and present it to the NLP Industry Advisory Board for review. For the remainder of the quarter, each team will complete the implementation of their project. At the conclusion of the quarter, each team will present their findings at a workshop or poster session that is open to the public. Students will gain experience on the design, implementation, and presentation of a substantial NLP team project.

10 credits
Quarter: Fall

Reviews recent work on conversational AI systems for task-oriented, informational, and social conversations with machines. Students read and review theoretical and technical papers from journals and conference proceedings, lectures and engage in discussions. A research project is required.
5 credits
Quarter: Winter, Spring

Gives students a solid foundation in a specific application area of natural language processing, by learning about the theories, methods, tools, and techniques typically used in this area. The application area varies each quarter, with expected topics to include Information Extraction, Question Answering, Natural Language Generation, Sentiment Analysis, and others. Students learn about the state of the art and open challenges, and have the opportunity to explore and experiment with both standard algorithms and new emerging approaches.
5 credits
Quarter: Winter, Spring

Machine Translation systems can instantly translate between any pair of over eighty human languages such as German to English or French to Russian. Modern translation systems learn to translate by reading millions of words of already translated text. This course covers the models and algorithms used by such systems and explains how they are able to automatically translate one human language to another. The course covers fundamental building blocks using concepts from linguistics, statistical and deep machine learning, algorithms, and data structures. It provides insight into the challenges associated with machine translation and introduces novel approaches that might lead to better machine translation systems.
5 credits
Quarter: Winter, Spring

Provides an introduction to theoretical linguistics for natural language processing, focusing on morphology, syntax, semantics, and pragmatics, and on training students in linguistic description, representation, and argumentation. Students learn to describe common features underlying natural languages and to manipulate several syntactic and semantic representations.
5 credits
Quarter: Winter, Spring

Focuses on classic and current theories and research topics in the computational modeling of discourse and dialogue, with applications to human-computer dialogue interactions; dialogue interaction in computer games and interactive story systems; and processing of human-to-human conversational and dialogue-like language such as e-mails. Topics vary depending on the current research of the instructor(s) and the interests of the students. Students read theoretical and technical papers from journals and conference proceedings and present class lectures. A research project is required.
5 credits
Quarter: Winter

Course covers major topics of information retrieval including: characteristics and representation of text, several important retrieval and ranking models, content recommendation and classification; distributed or federated search, AI semantics and dialog for information access; human factors and interfaces; and evaluation, and domain-specific applications. A research project is required.
5 credits
Quarter: Spring

In-depth study of current research topics in machine learning. Topics vary from year to year but include multi-class learning with boosting and SUM algorithms, belief nets, independent component analysis, MCMC sampling, and advanced clustering methods. Students read and present research papers; theoretical homework in addition to a research project.
5 credits
Quarter: Winter, Spring

Teaches participants about current methods and directions in active areas of Natural Language Processing research and applications. Students perform independent research and hone skills with state-of-the-art NLP tools and techniques.
5 credits
Quarter: Spring or Fall