We address the issue of using heterogeneous treebanks for parsing by breaking it down into two sub-problems, converting grammar formalisms of the treebanks to the same one, and pa...
We present a simple and effective framework for exploiting multiple monolingual treebanks with different annotation guidelines for parsing. Several types of transformation pattern...
Three state-of-the-art statistical parsers are combined to produce more accurate parses, as well as new bounds on achievable Treebank parsing accuracy. Two general approaches are ...
The creation of language resources for less-resourced languages like the historical ones benefits from the exploitation of language-independent tools and methods developed over th...
Abstract. This paper describes a method of adapting a domain-independent HPSG parser to a biomedical domain. Without modifying the grammar and the probabilistic model of the origin...