It is well known that among all probabilistic graphical Markov models the class of decomposable models is the most advantageous in the sense that the respective distributions can b...
We address the problem of pronunciation variation in conversational speech with a context-dependent articulatory featurebased model. The model is an extension of previous work usi...
Preethi Jyothi, Karen Livescu, Eric Fosler-Lussier
We discuss how to learn non-recursive directed probabilistic logical models from relational data. This problem has been tackled before by upgrading the structure-search algorithm i...
Daan Fierens, Jan Ramon, Maurice Bruynooghe, Hendr...
Abstract. This paper describes the process by which we are constructing an intelligent tutoring system (ERST) designed to improve learners’ external representation (ER) selection...
Identification of transliterations is aimed at enriching multilingual lexicons and improving performance in various Natural Language Processing (NLP) applications including Cross ...