Miriam Butt gave a talk last Friday, October 5. Miriam is
Professor of Linguistics and Chair of the Department of Linguistics
(Fachbereich Sprachwissenschaft) at the University of Konstanz. She is best known for her theoretical linguistic work on complex predicates and on grammatical case, and for her computational linguistic work in large-scale grammar development within the Pargram project. Recently she has been also involved in interdisciplinary work on the visualization of linguistic data.
The title, and abstract, of her talk was:
Deep Natural Language Processing
This talks provides a look at the capabilities of deep linguistic
natural lanuguage processing in the context of ParGram, an
international effort at building grammars for languages as diverse as
English, French, Welsh, Wolof, Georgian, Urdu, Japanese, Indonesian,Arabic and Murrinh-Patha. The aim is to build these grammars using not only the same theoretical assumptions (based on Lexical-Functional Grammar) but also the same computational methods. While the process of computational grammar devleopment is, of course, inherently interesting, we will also discuss the broader uses of computational grammars, for example in systems like IBM's Watson and Powerset's information retrieval system.
The underlying development platform XLE/XFR (used by Powerset and in the ParGram effort) was developed at PARC over a number of years. The talk will focus on the various powerful analysis possibilities this system allows for, including a version of Optimality Theory and an integration of statistical information to constrain and inform both parsing and generation. The talk will also touch on the assumptions about the underlying grammar architecture that are made, e.g., with respect to the morphology-syntax and the syntax-semantics interface.
