Probabilistic prediction and Picky chart parsing

This paper describes Picky, a probabilistic agenda-based chart parsing algorithm which uses a technique called probabilistic prediction to predict which grammar rules are likely to lead to an acceptable parse of the input. In tests on randomly selected test data, Picky generates fewer edges on average than other CKY-like algorithms, while achieving 89% first parse accuracy and also enabling the parser to process sentences with false starts and other minor disfluencies. Further, sentences which are parsed completely by the probabilistic prediction technique have a 97% first parse accuracy.