CS 485: Applications of Natural Language Processing

CS 485, Fall 2023, UMass Amherst CICS

Tuesdays and Thursdays, 2:30pm-3:45pm, Thompson 106
First day: Tues Sept. 5

Course staff:

• Instructor: Brendan O'Connor, office hours Wednesday, 3-4pm in CS 238. See the Piazza Resources page for hybrid Zoom link.
• TA: Erica Cai, office hours Thursday, 4-5pm in LGRT 220

Links:

• Course schedule webpage
• Projects webpage
• Piazza for general course communication
• Gradescope for assignment submission
• Moodle/Echo360 for lecture videos
• Contacting course staff: use a Piazza private message. To email the instructor, put "CS485" in your email's subject line, to brenocon@cs.umass.edu.

Syllabus

Course description

Natural Language Processing (NLP) is the engineering art and science of how to teach computers to understand human language. NLP is a type of artificial intelligence technology, and it's now ubiquitous -- NLP lets us talk to our phones, use the web to answer questions, map out discussions in books and social media, generate chatbot responses, and translate between human languages. Since language is rich, ambiguous, and very difficult for computers to understand, these systems can sometimes seem like magic -- but these are engineering problems we can tackle with data, math, and insights from linguistics.

This course introduces NLP methods and applications including probabilistic models, text classification, linguistic representations, and contextual neural language models to process, understand, and generate text. During the course, students will (1) learn the core methods for NLP; (2) become familiar with key facts about human language that motivate them, and help practitioners know what problems are possible to solve; (3) become equipped to engage critically with arguments about NLP’s ethical and social implica-tions; and (4) complete a series of hands-on projects to implement, experiment with, and improve NLP models, gaining practical skills for natural language systems engineering.

This course is intended for upper-level undergraduate students in computer science and linguistics.

Prerequisites: experience in programming and probability, from the courses
     (CS 220 and CS 240) or Ling 492B
This is intended to represent comfort with programming, and basic probability and algorithm analysis.

Related courses

See this list of UMass NLP courses.

Readings

• The main suggested textbook is Jurafsky and Martin, Speech and Language Processing, 3rd ed. Draft PDFs. We will post PDF readings from it.
• Also useful is Eisenstein, Natural Language Processing. Pre-print PDF (book also available). We will have some readings from it.

Other useful texts for NLP include:

• Bender, Linguistic Fundamentals for NLP. Short book. Focuses on linguisic issues relevant to NLP.
• Manning and Schütze, Foundations of Stat NLP. Free access at UMass.
• Smith, Linguistic Structure Prediction. Free access at UMass. Short book. Structured prediction inference methods for NLP.
• Murphy, Machine Learning: a Probabilistic Perspective. Excellent, though advanced, coverage of most of the machine learning methods we will use.
• Bird et al, NLP with Python, a.k.a. the NLTK book. Aimed at a more introductory level than this course, but the book is a good gentle introduction to NLP with a CL (computational linguistics) emphasis. The NLTK software has easy-to-use data access and some interfaces to (not always SOTA) NLP tools.