Learn More
This paper investigates semi-supervised methods for discriminative language modeling, whereby n-best lists are “hallucinated” for given reference text and are then used for training n-gram language models using the perceptron algorithm. We perform controlled experiments on a very strong baseline English CTS system, comparing three methods for(More)
We present our work on semi-supervised learning of discriminative language models where the negative examples for sentences in a text corpus are generated using confusion models for Turkish at various granularities, specifically, word, sub-word, syllable and phone levels. We experiment with different language models and various sampling strategies to select(More)
Discriminative language modeling is a structured classification problem. Log-linear models have been previously used to address this problem. In this paper, the standard dot-product feature representation used in log-linear models is replaced by a non-linear function parameterized by a neural network. Embeddings are learned for each word and features are(More)
Modelling and analysis of biochemical systems such as sugar cataract development (SCD) are critical because they can provide new insights into systems, which cannot be easily tested with experiments; however, they are challenging problems due to the highly coupled chemical reactions that are involved. The authors present a stochastic hybrid system (SHS)(More)
Modeling and analysis of chemical reactions are critical problems because they can provide new insights into the complex interactions between systems of reactions and chemicals. One such set of chemical reactions defines the creation of biodiesel from soybean oil and methanol. Modeling and analyzing the biodiesel creation process is a challenging problem(More)
The perceptron algorithm was used in [1] to estimate discrim-inative language models which correct errors in the output of ASR systems. In its simplest version, the algorithm simply increases the weight of n-gram features which appear in the correct (oracle) hypothesis and decreases the weight of n-gram features which appear in the 1-best hypothesis. In(More)
Stochastic hybrid system models can be used to analyze and design complex embedded systems that operate in the presence of uncertainty and variability. Verification of safety properties of such systems is a critical problem because of the interaction between the discrete and continuous stochastic dynamics. In this paper, we propose a probabilistic method(More)