We show that excluding outliers from the training data significantly improves kNN classifier, which in this case performs about 10% better than the best know method--Centroid-based...
The design of practical language applications by means of statistical approaches requires annotated data, which is one of the most critical constraint. This is particularly true f...
Marco Dinarelli, Alessandro Moschitti, Giuseppe Ri...
The purpose of this study is to generate weather forecasts from XML-stored weather dataset. Reiter and Dale (2000) proposes Natural Language Generation (NLG) System as three-stage...
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunki...
Research in natural language generation promises significant advances in the ways in which we can make available the contents of underlying information sources. Most work in the f...
Robert Dale, Stephen J. Green, Maria Milosavljevic...