A machine-learning approach to the identification of WH gaps

Abstract

In this paper, we pursue a multimodular, statistical approach to WH dependencies, using a feedforward network as our modeling tool. The empirical basis of this model and the availability of performance measures for our system address deficiencies in earlier computational work on WH gaps, which require richer sources of semantic and lexical information in order to run. The statistical nature of our models allows them to be simply combined with other modules of grammar, such as a syntactic parser.