6.864: About

Course Description:

Graduate introduction to natural language processing, the study of human language from a computational perspective. Syntactic, semantic and discourse processing models. Emphasis on machine learning or corpus-based methods and algorithms. Use of these methods and models in applications including syntactic parsing, information extraction, statistical machine translation, dialogue systems, and summarization.

This subject qualifies as an Artificial Intelligence and Applications concentration subject.

Syllabus:

• Introduction (1 lecture)
• Estimation techniques, and language modeling (1 lecture)
• Parsing and Syntax (5 lectures)
• The EM algorithm in NLP (1 lecture)
• Stochastic tagging, and log-linear models (2 lectures)
• Probabilistic similarity measures and clustering (2 lectures)
• Machine Translation (2 lectures)
• Discourse Processing: segmentation, anaphora resolution (3 lectures)
• Dialogue systems (1 lectures)
• Natural Language Generation/Summarization (1 lecture)
• Unsupervised methods in NLP (1 lecture)

Readings:

Course readings will be available either on the web or in-class handouts.

Academic Integrity:

Everything you do for credit in this subject is supposed to be your own work. You can talk to other students (and instructors) about approaches to problems, but then you should sit down and do the problem yourself. This is not only the ethical way but also the only effective way of learning the material.

Objectives:

• Understand approaches to syntax and semantics in NLP.
• Understand approaches to discourse, generation, dialogue and summarization within NLP.
• Understand current methods for statistical approaches to machine translation.
• Understand machine learning techniques used in NLP, including hidden markov models and probabilistic context-free grammars, clustering and unsupervised methods, log-linear and discriminative models, and the EM algorithm as applied within NLP.

Measurable Outcomes and Assessment Methods

• Understand the mathematical and linguistic foundations underlying approaches to the above areas in NLP (measured by problem sets and quizes).
• Design, implement and test algorithms for NLP problems (measured by problem sets).