This year we participated in the Novelty track. To find the relevant sentences, we combine sentence salience features that are inherited from text summarization domain with other ...
It is difficult to identify sentence importance from a single point of view. In this paper, we propose a learning-based approach to combine various sentence features. They are cat...
LASSO (Least Absolute Shrinkage and Selection Operator) is a useful tool to achieve the shrinkage and variable selection simultaneously. Since LASSO uses the L1 penalty, the optim...
We are studying long term sequence prediction (forecasting). We approach this by investigating criteria for choosing a compact useful state representation. The state is supposed t...
Coreference systems are driven by syntactic, semantic, and discourse constraints. We present a simple approach which completely modularizes these three aspects. In contrast to muc...