Paper: Characterizing the Errors of Data-Driven Dependency Parsing Models

ACL ID D07-1013
Title Characterizing the Errors of Data-Driven Dependency Parsing Models
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2007
Authors

We present a comparative error analysis of the two dominant approaches in data- driven dependency parsing: global, exhaus- tive, graph-based models, and local, greedy, transition-based models. We show that, in spite of similar performance overall, the two models produce different types of errors, in a way that can be explained by theoretical properties of the two models. This analysis leads to new directions for parser develop- ment.