A framework is summarized which supports the planning of natural language argument structure. One key aspect of natural argument is the order in which components are presented. Th...
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...
Hidden markov models (HMMs) and prediction by partial matching models (PPM) have been successfully used in language processing tasks including learning-based token identification. ...
Event semantics in general and event type coercion in particular have been a challenging yet rewarding topic in verbal semantics (Pustejovsky, 1995). However, there have been few ...
We examine effects that empty categories have on machine translation. Empty categories are elements in parse trees that lack corresponding overt surface forms (words) such as drop...