An alternative to head-driven approaches for parsing a (relatively) free word-order language

Abstract

Applying statistical parsers developed for English to languages with freer word-order has turned out to be harder than expected. This paper investigates the adequacy of different statistical parsing models for dealing with a (relatively) free word-order language. We show that the recently proposed Relational-Realizational (RR) model consistently outperforms state-of-the-art Head-Driven (HD) models on the Hebrew Treebank. Our analysis reveals a weakness of HD models: their intrinsic focus on configurational information. We conclude that the form-function separation ingrained in RR models makes them better suited for parsing nonconfigurational phenomena. © 2009 ACL and AFNLP.