Speaker: Xavier Carreras, LSI UPC <br />Time: tuesday, feb 9th, 15:30 <br />Place: S208, floor -2, Omega Building<br /> <br />Title: A TAG formalism for Parsing and Translation <br /> <br />Abstract: <br />Syntactic parsing is the fundamental problem of determining the structure of natural language sentences. It is a challenging task, because syntactic structures of natural languages are recursive, and there is a significant degree of ambiguity in determining how different parts of a sentence combine together syntactically. <br /> <br />In any computational model for parsing, the choice of grammar formalism is critical to both&nbsp; the representational power of the model and its computational efficiency. In this talk I will describe a variant of a Tree Adjoining Grammar (TAG) that can use a wide varitey of rich features and, at the same time, has efficient algorithms. <br /> <br />I will present two applications of our TAG. The first is a discriminative parser, a generalization of Conditional Random Fields for sequence prediction that extends the framework to syntactic parsing. I will then present a system for Machine Translation that frames the task of translation as a parsing task. <br /> <br />No previous NLP knowledge required. This is joint work with Michael Collins and Terry Koo. <br /><br />