PCFG models of linguistic tree representations

Abstract

This paper points out that the Penn lI treebank representations are of the kind predicted to have such an effect, and describes a simple node relabeling transformation that improves a treebank PCFG-based parser's average precision and recall by around 8%, or approximately half of the performance difference between a simple PCFG model and the best broad-coverage parsers available today. This performance variation comes about because any PCFG, and hence the corpus of trees from which the PCFG is induced, embodies independence assumptions about the distribution of words and phrases. The particular independence assumptions implicit in a tree representation can be studied theoretically and investigated empirically by means of a tree transformation / detransformation process