We propose a new unsupervised learning technique for extracting information about authors and topics from large text collections. We model documents as if they were generated by a...
Michal Rosen-Zvi, Chaitanya Chemudugunta, Thomas L...
The Robust Self-Configuring Embedded Systems (RoSES) project seeks to achieve graceful degradation through software reconfiguration. To accomplish this goal, systems must automati...
We present a dialogue system for exercising the German subordinate clause word order. The pedagogical methodology we adopt is based on focused tasks: the targeted linguistic struct...
Language model (LM) adaptation is important for both speech and language processing. It is often achieved by combining a generic LM with a topic-specific model that is more releva...
This paper considers the theory of database queries on the complex value data model with external functions. Motivated by concerns regarding query evaluation, we first identify re...