Scoring sentences in documents given abstract summaries created by humans is important in extractive multi-document summarization. In this paper, we formulate extractive summariza...
The standard model of supervised learning assumes that training and test data are drawn from the same underlying distribution. This paper explores an application in which a second...
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
We propose a novel boosting algorithm which improves on current algorithms for weighted voting classification by striking a better balance between classification accuracy and the ...
If the promise of computational modeling is to be fully realized in higherlevel cognitive domains such as language processing, principled methods must be developed to construct th...