Peter T. Pham

Learn More
Unsupervised vector-based approaches to semantics can model rich lexical meanings, but they largely fail to capture sentiment information that is central to many word meanings and important for a wide range of NLP tasks. We present a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term–document(More)
In recent years, deep learning approaches have gained significant interest as a way of building hierarchical representations from unlabeled data. However, to our knowledge, these deep learning approaches have not been extensively studied for auditory data. In this paper, we apply convolutional deep belief networks to audio data and empirically evaluate them(More)
This document received 22 “You rock” reactions, 1 “Teehee” reaction, and 1 “Wow, just wow.” reaction. We can treat these reactions as a normalized distribution over reactions, [0.916, 0.041, 0, 0, 0.041]. Treating the reaction data as a normalized distribution allows us to ignore the differences in reaction counts across documents and instead focus only on(More)
OBJECTIVE Recent surveillance data suggests the United States (U.S.) Army HIV epidemic is concentrated among men who have sex with men. To identify potential targets for HIV prevention strategies, the relationship between demographic and clinical factors and membership within transmission clusters based on baseline pol sequences of HIV-infected Soldiers(More)
In humans, cytochrome P450 1A2 is the major enzyme metabolizing environmental arylamines or heterocyclic amines into carcinogens. Since evidence shows that planar triangle-shaped molecules are capable of selectively inhibiting P450 1A2, 16 triangular flavone, and coumarin derivatives were designed and synthesized for these studies. Among these compounds,(More)
  • 1