Paper: Perceptron Reranking for CCG Realization

ACL ID D09-1043
Title Perceptron Reranking for CCG Realization
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2009
Authors

This paper shows that discriminative reranking with an averaged perceptron model yields substantial improvements in realization quality with CCG. The paper confirms the utility of including language model log probabilities as features in the model, which prior work on discrimina- tive training with log linear models for HPSG realization had called into question. Theperceptronmodelallowsthecombina- tion of multiple n-gram models to be opti- mized and then augmented with both syn- tactic features and discriminative n-gram features. The full model yields a state- of-the-art BLEU score of 0.8506 on Sec- tion 23 of the CCGbank, to our knowledge the best score reported to date using a re- versible, corpus-engineered grammar.