A Discriminative Model for Joint Morphological Disambiguation and Dependency Parsing

Most previous studies of morphological disambiguation and dependency parsing have been pursued independently. Morphological taggers operate on n-grams and do not take into account syntactic relations; parsers use the “pipeline” approach, assuming that morphological information has been separately obtained. However, in morphologically-rich languages, there is often considerable interaction between morphology and syntax, such that neither can be disambiguated without the other. In this paper, we propose a discriminative model that jointly infers morphological properties and syntactic structures. In evaluations on various highly-inflected languages, this joint model outperforms both a baseline tagger in morphological disambiguation, and a pipeline parser in head selection.

• Type: Journal
• Year: 2011
• Where: ACL
• Authors: John Lee, Jason Naradowsky, David A. Smith
• Keywords: ACL 2011, Computational Linguistics, Morphological Disambiguation, Pipeline Approach, Rich Languages