We describe a method for enriching the output of a parser with information available in a corpus. The method is based on graph rewriting using memorybased learning, applied to dep...
Many state-of-the-art statistical parsers for English can be viewed as Probabilistic Context-Free Grammars (PCFGs) acquired from treebanks consisting of phrase-structure trees enri...
We describe a natural language parser that uses type information to determine the grammatical structure of simple sentences and phrases. This stands in contrast to studies of type...
This paper proposes a new class-based method to estimate the strength of association in word co-occurrence for the purpose of structural disambiguation. To deal with sparseness of...
We present an integrated approach to speech and natural language processing which uses a single parser to create training for a statistical speech recognition component and for in...