Paper: A Constraint Satisfaction Approach to Dependency Parsing

ACL ID D07-1121
Title A Constraint Satisfaction Approach to Dependency Parsing
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2007
Authors

We present an adaptation of constraint satis- faction inference (Canisius et al. , 2006b) for predicting dependency trees. Three differ- ent classifiers are trained to predict weighted soft-constraints on parts of the complex out- put. From these constraints, a standard weighted constraint satisfaction problem can be formed, the solution to which is a valid dependency tree.