Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...
We propose a low cost method for the correction of the output of OCR engines through the use of human labor. The method employs an error estimator neural network that learns to as...
Whether knowingly or otherwise, Wikipedia contributors reveal their interests and expertise through their contribution patterns. An analysis of Wikipedia edit histories shows that...
Many applications need to solve the problem of approximate string matching with block moves. It is an NP-Complete problem to compute block edit distance between two strings. Our go...
Estimation of distribution algorithms (EDAs) that use marginal product model factorizations have been widely applied to a broad range of, mainly binary, optimization problems. In ...