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...
Many statistical translation models can be regarded as weighted logical deduction. Under this paradigm, we use weights from the expectation semiring (Eisner, 2002), to compute fir...
Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...
We propose methods to classify lines of military chat, or posts, which contain items of interest. We evaluated several current text categorization and feature selection methodologi...
The Pedagogical Assessment Workflow System (PAWS) is a new workflow-based pedagogical assessment framework that enables the efficient and robust integration of diverse datasets for...