High performance logic form transformation

摘要

This paper presents extensions to a previously developed logic form representation and a method for transforming WordNet glosses into logic forms using a set of high-precision rules combined with a set of high recall heuristics. An almost 3% increase in P05 tagging accuracy is achieved over state-of-the art results at the expense of user intervention on only 7.52% of words. We apply a nearest neighbor solution to parser switching that leads to 6.43% increase in exact sentence accuracy for glosses. Logic Forms are derived with an accuracy of 89.46%.