We show that naïve modeling of morphosyntactic agreement in a Constituency-Based (CB) statistical parsing model is worse than none, whereas a linguistically adequate way of modeling inflectional morphology in CB parsing leads to improved performance. In particular, we show that an extension of the Relational-Realizational (RR) model that incorporates agreement features is superior to CB models that treat morphosyntax as state-splits (SP), and that the RR model benefits more from inflectional features. We focus on parsing Hebrew and report the best result to date, F184.13 for parsing off of gold-tagged text, 5% error reduction from previous results.
|Number of pages||9|
|State||Published - 2010|
|Event||1st Workshop on Statistical Parsing of Morphologically-Rich Languages, SPMRL 2010 - Los Angeles, United States|
Duration: 5 Jun 2010 → …
|Conference||1st Workshop on Statistical Parsing of Morphologically-Rich Languages, SPMRL 2010|
|Period||5/06/10 → …|
Bibliographical noteFunding Information:
The work of the first author has been funded by NWO, grant 017.001.271. We wish to thank Joakim Nivre and three anonymous reviewers for helpful comments on earlier drafts.
© 2010 Association for Computational Linguistics