Showing papers in "Progress in Artificial Intelligence in 2003"
Journal Article•
TL;DR: This work not only reviews relevant linguistic literature but also re-examine relevant issues from a new statistical and corpus point of view, and discovers more comprehensive and precise question-related words than before.
Abstract: Detecting Mandarin question sentences is both interesting and difficult. To tackle this new topic, our strategy is first to try to increase recall and then precision. To achieve higher recall, we not only review relevant linguistic literature but also re-examine relevant issues from a new statistical and corpus point of view, and discover more comprehensive and precise question-related words than before. Next we present our statistical approaches and procedure, and discuss our findings. We achieve good recall and modest precision in the preliminary study, and pioneer the computational study of indefinitives.
2 citations
Journal Article•
TL;DR: In this paper, EAs using direct representations are applied to several classification and regression ANN learning tasks, and EAs are also combined with local optimization under the Lamarckian framework.
Abstract: Several gradient-based methods have been developed for Artificial Neural Network (ANN) training. Still, in some situations, such procedures may lead to local minima, making Evolutionary Algorithms (EAs) a promising alternative. In this work, EAs using direct representations are applied to several classification and regressionANN learning tasks. Furthermore, EAs are also combined with local optimization, under the Lamarckian framework. Both strategies are compared with conventional training methods. The results reveal an enhanced performance by a macro-mutation based Lamarckian approach.
1 citations