Parse correction with specialized models for difficult attachment types

Enrique Henestroza Anguiano (1) , Marie Candito (1)

1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing

This paper develops a framework for syntactic dependency parse correction. Dependencies in an input parse tree are revised by selecting, for a given dependent, the best governor from within a small set of candidates. We use a discriminative linear ranking model to select the best governor from a group of candidates for a dependent, and our model includes a rich feature set that encodes syntactic structure in the input parse tree. The parse correction framework is parser-agnostic, and can correct attachments using either a generic model or specialized models tailored to difficult attachment types like coordination and pp-attachment. Our experiments show that parse correction, combining a generic model with specialized models for difficult attachment types, can successfully improve the quality of predicted parse trees output by several representative state-of-the-art dependency parsers for French.

Domaines: Informatique et langage [cs.CL]; Traitement du texte et du document

Enrique Henestroza Anguiano, Marie Candito. Parse correction with specialized models for difficult attachment types. EMNLP 2011 - The 2011 Conference on Empirical Methods in Natural Language Processing, Jul 2011, Edinburgh, United Kingdom. To appear. ⟨hal-00602083⟩