• Publications
  • Influence
Does String-Based Neural MT Learn Source Syntax?
TLDR
We investigate whether a neural, encoderdecoder translation system learns syntactic information on the source side as a by-product of training. Expand
  • 213
  • 24
  • PDF
Serum sclerostin levels negatively correlate with parathyroid hormone levels and free estrogen index in postmenopausal women.
CONTEXT Sclerostin is a negative regulator of bone formation. OBJECTIVE The aim of the study was to compare serum sclerostin levels in premenopausal and postmenopausal women and evaluate itsExpand
  • 268
  • 6
Torsades de Pointes associated with intravenous haloperidol in critically ill patients.
In this retrospective case-control study, 8 of 223 consecutive patients (3.6%) treated with intravenous haloperidol developed torsades de pointes, and were compared with 41 patients randomly selectedExpand
  • 195
  • 5
Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer
TLDR
We propose a new method for training encoder-decoders using non-parallel data that combines a collaborative classifier, attention and the cycle consistency loss that outperforms a state-of-the-art text style transfer system in two out of three quantitative metrics. Expand
  • 44
  • 3
  • PDF
Characterization of gentamicin pharmacokinetics in patients hemodialyzed with high-flux polysulfone membranes.
To characterize the pharmacokinetics of gentamicin during and after hemodialysis (using polysulfone Fresenius F-80 membranes (Fresenius USA, Inc, Walnut Creek, CA), surface area 1.6 m(2)), eightExpand
  • 31
  • 2
A randomized, double-blind comparison of intravenous diltiazem and digoxin for atrial fibrillation after coronary artery bypass surgery.
BACKGROUND Atrial fibrillation (AF) after coronary bypass graft surgery may result in hypotension, heart failure symptoms, embolic complications, and prolongation in length of hospital stay (LOHS).Expand
  • 81
  • 1
Improved Neural Text Attribute Transfer with Non-parallel Data
TLDR
We propose a novel algorithm for text attribute transfer with non-parallel corpora based on the encoder-decoder architecture with attention, augmented with the collaborative classifier and a set of content preservation losses. Expand
  • 15
  • 1
  • PDF
Learning Implicit Generative Models by Matching Perceptual Features
TLDR
We propose a new effective MM approach that learns implicit generative models by performing mean and covariance matching of features extracted from pretrained convolutional layers of pretrained ConvNets. Expand
  • 5
  • 1
  • PDF
PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences
TLDR
We report a peptide generation framework PepCVAE, based on a semi-supervised variational autoencoder (VAE) model, for designing novel antimicrobial peptide (AMP) sequences. Expand
  • 5
  • 1
  • PDF
Atrial fibrillation after bypass surgery: does the arrhythmia or the characteristics of the patients prolong hospital stay?
STUDY OBJECTIVES The goal of this study was to determine whether prolonged hospital stay associated with atrial fibrillation or flutter (AF) after coronary artery bypass graft (CABG) surgery isExpand
  • 113