We describe how we used a data set of chorale harmonisations composed by Johann Sebastian Bach to train Hidden Markov Models. Using a probabilistic framework allows us to create a...
We introduce a novel mechanism for incorporating articulatory dynamics into speech recognition with the theory of task dynamics. This system reranks sentencelevel hypotheses by th...
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
This paper studies the problem of mining relational data hidden in natural language text. In particular, it approaches the relation classification problem with the strategy of tra...