This course will explore current statistical techniques for the automatic analysis of natural (human) language data. The dominant modeling paradigm is corpus-driven supervised learning, but unsupervised methods and even hand-coded rule-based systems will be mentioned when appropriate.

In the first part of the course, we will examine the core tasks in natural language processing, including language modeling, word-sense disambiguation, morphological analysis, part-of-speech tagging, syntactic parsing, semantic interpretation, coreference resolution, and discourse analysis. In each case, we will discuss which linguistic features are relevant to the task, how to design efficient models which can accommodate those features, and how to estimate parameters for such models in data-sparse contexts. In the second part of the course, we will explore how these core techniques can be applied to user applications such as information extraction, question answering, speech recognition, machine translation, and interactive dialog systems.

Course assignments will highlight several core NLP tasks. For each task, we will construct a basic system, then improve it through a cycle of linguistic error analysis and model redesign. There will also be a final project, which will investigate a single topic or application in greater depth. This course assumes a familiarity with basic probability and the ability to program in Java. Prior experience with linguistics or natural languages is helpful, but not required.  Disclaimer: there will be a lot of statistics and algorithms in this class, as well as some serious coding.

Readings

The texts for this course are:

• Manning and Shuetze, Foundations of Statistical Natural Language Processing [amazon.com] [online version]
• Jurafsky and Martin, Speech and Language Processing [amazon.com] [updates online]

I recommend both, but most of what you need is online.

Syllabus [subject to change!]