Paper: Vine Parsing And Minimum Risk Reranking For Speed And Precision

ACL ID W06-2929
Title Vine Parsing And Minimum Risk Reranking For Speed And Precision
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2006
Authors

We describe our entry in the CoNLL-X shared task. The system consists of three phases: a probabilistic vine parser (Eisner and N. Smith, 2005) that pro- duces unlabeled dependency trees, a probabilistic relation-labeling model, and a discriminative mini- mum risk reranker (D. Smith and Eisner, 2006). The system is designed for fast training and decoding and for high precision. We describe sources of cross- lingual error and ways to ameliorate them. We then provide a detailed error analysis of parses produced for sentences in German (much training data) and Arabic (little training data).