Linguistics Courses

Introduction to Linguistic Phonetics (5 credits)
Introduction to the articulatory and acoustic correlates of phonological features. Issues covered include the mapping of dynamic events to static representations, phonetic evidence for phonological description, universal constraints on phonological structure, and implications of psychological speech-sound categorization for phonological theory.

Introduction to Syntax for Computational Linguistics (3 credits) Introduction to syntactic analysis and concepts (including part of speech types, constituent structure, the syntax-semantics interface, and phenomena such as complementation, raising, control, passive, and long-distance dependencies). Emphasis will be placed on formally precise encoding of linguistic hypotheses and designing grammars so that they can be scaled up for practical applications. Through the course we will progressively build up a consistent grammar for a fragment of English. Problem sets will introduce data and phenomena from other languages.

Computational Linguistics Courses

Note: These courses are arranged mostly according to subproblems in the field of computational linguistics. A few themes cut across these subproblems, and will be accordingly addressed in each appropriate class, from the perspective of that class. Those themes include: evaluation, ambiguity resolution, and the reusability of resources and techniques across languages. Most of the courses will be hands-on, with weekly lab assignments and/or implemented term projects.

Shallow Processing Techniques for Natural Language Processing (4 credits)
Techniques and algorithms for associating relatively surface-level structures and information with natural language corpora, including: POS tagging, morphological analysis, preprocessing/segmentation, named entity recognition, chunk parsing, and word-sense disambiguation. Linguistic resources that can be leveraged for these tasks (e.g., WordNet).

Deep Processing Techniques for Natural Language Processing(4 credits)
This course covers algorithms for using precision grammars to associate deep or elaborated linguistic structures with naturally occurring linguistic data (parsing), and to associate natural language strings with input semantic representations (generation). It also covers associated techniques for disambiguation (parse, generated string) and transfer (for symbolic machine translation).

Advanced Statistical Methods in Natural Language Processing (4 credits)
Statistical approaches to applications such as machine translation, automated lexical acquisition (monolingual and bilingual), information retrieval, and question answering, with components including language modeling, alignment, and document clustering.

Natural Language Processing Systems and Applications (4 credits)
This course looks at building coherent systems designed to tackle practical applications. Particular topics will vary year to year, but each class will consider some of the following: machine (aided) translation, speech interfaces, information retrieval/extraction, natural language query systems, dialogue systems, augmentative and alternative communication, computer assisted language learning, language documentation/linguistic hypothesis testing, spell/grammar checking, OCR, handwriting recognition, and software localization.

View list of elective courses.