We propose a new discriminative framework, namely Hidden Dynamic Conditional Random Fields (HDCRFs), for building probabilistic models which can capture both internal and external...
We present a simple history-based model for sentence generation from LFG f-structures, which improves on the accuracy of previous models by breaking down PCFG independence assumpt...
Current formal models for quantum computation deal only with unitary gates operating on “pure quantum states”. In these models it is difficult or impossible to deal formally w...
We present a new ensemble method that uses Entropy Guided Transformation Learning (ETL) as the base learner. The proposed approach, ETL Committee, combines the main ideas of Baggin...
Discovering users' specific and implicit geographic intention in web search can greatly help satisfy users' information needs. We build a geo intent analysis system that...