When the 4-state or the 6-state protocol of quantum cryptography is carried out on a noisy quantum channel, then the raw key has to be processed to reduce the information of a spy down to an arbitrarily low value, providing Alice and Bob with a secret key. In principle, quantum algorithms as well as classical algorithms can be used for this processing. A natural question is: Up to which error r...

This article describes the implementation of Word Sense Disambiguation system that participated in the SemEval-2007 multilingual Chinese-English lexical sample task. We adopted a supervised learning approach with Maximum Entropy classifier. The features used were neighboring words and their part-of-speech, as well as single words in the context, and other syntactic features based on shallow par...

The problem of identifying voice commands has always been a challenge due to the presence of noise and variability in speed, pitch, etc. We will compare the efficacies of several neural network architectures for the speech recognition problem. In particular, we will build a model to determine whether a one second audio clip contains a particular word (out of a set of 10), an unknown word, or si...

Fifty-five word stories are brief pieces of creative writing that use elements of poetry, prose, or both to encapsulate key experiences in health care. These stories have appeared in Family Medicine and JAMA and have been used to teach family medicine faculty development fellows. Writers and readers of 55-word stories gain insight into key moments of the healing arts; the brevity of the pieces ...

This paper focuses on a key aspect of Statistical Machine Translation: word alignment. Various word alignment models are presented, first differentiating between methods and then highlighting the preferred method. A partially detailed mathematical explanation is provided for each model as well as a brief implementation of the Expectation Maximization Algorithm (EM Algorithm) for later models. F...