Abstract
When a parser processes a long sentence, it produces a lot of the parsing results because of the ambiguity. The number of parsing results and the processing time increase in proportion to the ambiguity. Stochastic approaches are widely used to reduce ambiguity in recent years. They add preference information learned by some stochastic methods to grammatical constraints. However, it is not desirable from a viewpoint of modularity of knowledge. In this paper, we separate preference information and grammatical constraints. When the parser processes a sentence, these information are integrated and used. We use probabilistic dependency relation as the source information for the reduction of ambiguity. In order to use this information, we modify the Chart parsing algorithm. Then, we can use stochastic information and grammatical constraints in an integrated manner, and also make the Chart parser efficient. The result of the experiment shows that the number of edges in the Chart decreases to one forth, and the processing time to one seventh.
