High precision logic form transformation
Abstract
This paper presents few extensions to the 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 POS 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%.
Publication Title
Proceedings of the International Conference on Tools with Artificial Intelligence
Recommended Citation
Rus, V. (2001). High precision logic form transformation. Proceedings of the International Conference on Tools with Artificial Intelligence, 288-295. Retrieved from https://digitalcommons.memphis.edu/facpubs/2865