Ordering information is a critical task for natural language generation applications. In this paper we propose an approach to information ordering that is particularly suited for ...
Abstract: The goal of information extraction (IE) is to find desired pieces of information in natural language texts and store them in a form that is suitable for automatic queryi...
Abstract We describe an event-based, publishand-subscribe system based on using "smart subscriptions" to recognize weakly structured events. We present a hierarchy of sub...
: Noncanonical semantic representations are representations which cannot be derived by some grammar G although they are semanticMly equivalent to representations which can be deriv...
We recapitulate regular one-shot learning from membership and equivalence queries, positive and negative finite data. We present a meta-algorithm that generalizes over as many sett...