Symbolic representations have been used successfully in off-line planning algorithms for Markov decision processes. We show that they can also improve the performance of online p...
Precision achieved by stochastic sampling algorithms for Bayesian networks typically deteriorates in face of extremely unlikely evidence. To address this problem, we propose the E...
We consider the problem belief-state monitoring for the purposes of implementing a policy for a partially-observable Markov decision process (POMDP), specifically how one might ap...
The Lexical Access Problem consists of determining the intended sequence of words corresponding to an input sequence of phonemes (basic speech sounds) that come from a low-level p...
Ian E. Thomas, Ingrid Zukerman, Jonathan J. Oliver...
This paper proposes a segmentation standard for Chinese natural language processing. The standard is proposed to achieve linguistic felicity, computational feasibility, and data u...