Algorithms for associating deep or elaborated linguistic structures with naturally occurring linguistic data (parsing/semantics/discourse), and to produce natural language strings from input semantic representations (generation). Prerequisite: a minimum grade of 2.7 in each of CSE 326 or equivalent, STAT 391 or equivalent, and LING 473 or passing score on the placement exam. Offered: A.
This course covers algorithms for associating deep or elaborated linguistic structures with naturally occurring data, covering parsing, semantics, and discourse.
Student learning goals
Implement parsing algorithms to extract syntactic structure from sentences.
Employ probabilistic models to provide robust, ranked syntactic analysis of sentences based on training corpora.
Become familiar with resources for syntactic, semantic, and discourse analysis, including the Penn Treebank, WordNet, FrameNet, and the Penn Discourse Treebank.
Assess the utility of different syntactic models, including constituent and dependency analyses
Understand a range of techniques for performing word sense disambiguation
Gain insight into the structure of extended spans of text or speech (discourse)
General method of instruction
Class assignments and grading