In this paper we propose a data intensive approach for inferring sentence-internal temporal relations, which relies on a simple probabilistic model and assumes no manual coding. W...
We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. W...
State-of-the-art pronoun interpretation systems rely predominantly on morphosyntactic contextual features. While the use of deep knowledge and inference to improve these models wo...
Andrew Kehler, Douglas E. Appelt, Lara Taylor, Ale...
Maximum entropy models are a common modeling technique, but prone to overfitting. We show that using an exponential distribution as a prior leads to bounded absolute discounting b...
Many probabilistic models for natural language are now written in terms of hierarchical tree structure. Tree-based modeling still lacks many of the standard tools taken for grante...