HIGH PERFORMANCE LOGIC FORM TRANSFORMATION
Authors:
- 1 September 2002
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 11 (03) , 437-454
Abstract
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 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 of parser switching that leads to 6.43% increase in exact sentence accuracy for glosses. Logic Forms are derived with an accuracy of 89.46%.Keywords
This publication has 3 references indexed in Scilit:
- A parallel system for text inference using marker propagationsIEEE Transactions on Parallel and Distributed Systems, 1998
- WordNetCommunications of the ACM, 1995
- Interpretation as abductionArtificial Intelligence, 1993