13 August 2008, Computational Linguistics Seminar, Reut Tsarfaty

State-of-the-art statistical parsing models applied to free word-order languages tend to underperform compared to, e.g., parsing English. Constituency-based models often fail to capture generalizations that cannot be stated in structural terms, and dependency-based models employ a ~single-head~ assumption that often breaks in the face of multiple exponence. In this paper we suggest that the position of a constituent is a form manifestation of its grammatical function, one among various possible means of realization. We develop the Relational-Realizational approach to parsing in which we untangle the projection of grammatical functions and their means of realization to allow for phrase-structure variability and morphological-syntactic interaction. We empirically demonstrate the application of our approach to parsing Modern Hebrew, obtaining 7% error reduction from previously reported results.

For more information, see http://www.illc.uva.nl/LaCo/CLS/ or http://staff.science.uva.nl/~rtsarfat/coling08.pdf