Speaker | Stefan Riezler |
Date | Mar 14, 2014 |
Time | 11:00AM 12:00PM |
Location | IF 4.31/4.33 |
Title | Theoretical and Practical Grounding in Empirical Computational Linguistics |
Abstract | Philosophy of science has pointed out a circularity problem inempirical sciences that arises if all known measuring procedures for aquantity of a theory presuppose the validity of this theory. We discusshow this problem relates to empirical computational linguistics, anddefine a criterion of T-non-theoretical grounding as guidance to avoidsuch circularities. We exemplify how this criterion can be met bycrowdsourcing, task-related data annotation, or data in the wild. Inparticular, we illustrate the benefits of grounded learning in the areaof statistical machine translation, e.g., by grounding machinetranslation in a retrieval task for improved cross-lingual retrieval.
|
Bio | Prof. Stefan Riezler has been appointed full professor and head of thechair of Linguistic Informatics at Heidelberg University in 2010, afterspending a decade in the world’s most renowned industry research labs(Xerox PARC, Google). He received his PhD in Computational Linguisticsfrom the University of Tübingen in 1998, and then conductedpost-doctoral work at Brown University in 1999. Prof. Riezler'sresearch focus is on machine learning and statistics applied to naturallanguage processing problems, especially for the application areas ofnatural-language based web search and statistical machine translation.
|