Eukaryotic cells have developed elaborate biochemical processes to counteract oxidative stress, electrophiles, or carcinogens due to environmental insults. One of these important cellular defense mechanisms is mediated by the transcription factor Nrf2 that have been shown to have decrease activity with age. While the process of which Nrf2 is involved...
Automatic music transcription (AMT) is the task, given an acoustic representation of music, to recover a symbolic notation of the written notes expressed by the sound. Transcribing music with multiple notes sounding simultaneously is difficult for both humans and machines. Much existing work on AMT has focused on suitable acoustic...
Simultaneous translation, which translates concurrently with the source language speech, is widely used in many scenarios including multilateral organizations. However, it is well known to be one of the most challenging tasks for humans due to the simultaneous perception and production in two languages. On the other hand, simultaneous translation...
RNA secondary structure prediction maps a RNA sequence to its secondary structure (set of AU, CG, and GU pairs). It is an important problem in computational biology be-cause such structures reveals crucial information about the RNAs function, which is useful in many applications ranging from noncoding RNA detection to folding...
RNA structure prediction is a challenging problem, especially with pseudoknots. Recently, there has been a shift from the classical minimum free energy-based methods (MFE) to partition function-based ones that assemble structures based on base-pairing probabilities. Two typical examples of the latter group are the popular maximum expected accuracy (MEA) method...
Machine learning models for natural language processing have traditionally relied on large numbers of discrete features, built up from atomic categories such as word forms and part-of-speech labels, which are considered completely distinct from each other. Recently however, the advent of dense feature representations coupled with deep learning techniques has...
Most tasks in natural language processing (NLP) try to map structured input (e.g., sentence or word sequence) to some form of structured output (tag sequence, parse tree, semantic graph, translated/paraphrased/compressed sentence), a problem known as “structured prediction”. While various learning algorithms such as the perceptron, maximum entropy, and expectation-maximization have...
Most tasks in natural language processing (NLP) involves structured information from both input (e.g., a sentence or a paragraph) and output (e.g., a tag sequence, a parse tree or a translated sentence). While neural models achieve great successes in other domains such as computer vision, applying those frameworks to NLP...
The role of nanotopographical extracellular matrix (ECM) cues in vascular endothelial cell (EC) organization and function is not well-understood, despite the composition of nano- to microscale fibrillar ECMs within blood vessels. Instead, the predominant modulator of EC organization and function is traditionally thought to be hemodynamic shear stress, in which...