This paper proposes a method of correcting annotation errors in a treebank. By using a synchronous grammar, the method transforms parse trees containing annotation errors into the...
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model...
We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. HBG incorporates...
Ezra Black, Frederick Jelinek, John D. Lafferty, D...
Despite its state-of-the-art performance, the Data Oriented Parsing (DOP) model has been shown to suffer from biased parameter estimation, and the good performance seems more the ...