• Publications
  • Influence
Bayesian Face Revisited: A Joint Formulation
TLDR
In this paper, we revisit the classical Bayesian face recognition method by Baback Moghaddam et al. and propose a new joint formulation. Expand
  • 388
  • 62
  • PDF
Clinical information extraction applications: A literature review
  • Yanshan Wang, Liwei Wang, +8 authors H. Liu
  • Computer Science, Medicine
  • J. Biomed. Informatics
  • 2018
TLDR
We present a literature review of recent published research on clinical information extraction (IE) applications. Expand
  • 243
  • 9
  • PDF
MedSTS: a resource for clinical semantic textual similarity
  • Yanshan Wang, N. Afzal, +4 authors H. Liu
  • Computer Science
  • Lang. Resour. Evaluation
  • 28 August 2018
TLDR
The adoption of electronic health records (EHRs) has enabled a wide range of applications leveraging EHR data. Expand
  • 35
  • 9
  • PDF
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP
TLDR
A fundamental question in reinforcement learning is whether model-free algorithms are sample efficient. Expand
  • 37
  • 8
  • PDF
Deep Extreme Multi-label Learning
TLDR
We propose a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously. Expand
  • 45
  • 6
  • PDF
A Comparison of Word Embeddings for the Biomedical Natural Language Processing
  • Yanshan Wang, Sijia Liu, +5 authors H. Liu
  • Computer Science, Medicine
  • J. Biomed. Informatics
  • 1 February 2018
TLDR
We empirically evaluated word embeddings trained from four different corpora, namely clinical notes, biomedical publications, Wikipedia, and news. Expand
  • 141
  • 5
  • PDF
Constant-Parameter $RL$-Branch Equivalent Circuit for Interfacing AC Machine Models in State-Variable-Based Simulation Packages
TLDR
This paper considers the state-variable-based simulation packages and provides a constant-parameter decoupled RL-branch equivalent circuit for interfacing the ac induction and synchronous machine models with the external electrical network. Expand
  • 30
  • 5
Indexing the Past, Present and Future Positions of Moving Objects on Fixed Networks
TLDR
The development of a spatio-temporal access method suitable for objects moving on fixed networks is a very attractive challenge due to a large number of applications dealing with this type of objects. Expand
  • 19
  • 4
  • PDF
Smoothness, Disagreement Coefficient, and the Label Complexity of Agnostic Active Learning
  • Liwei Wang
  • Mathematics, Computer Science
  • J. Mach. Learn. Res.
  • 1 February 2011
TLDR
We study the disagreement coefficient of classification problems for which the classification boundary is smooth and data distribution has a density that can be bounded by a smooth function. Expand
  • 47
  • 2
  • PDF
Learning structural motif representations for efficient protein structure search
TLDR
We develop DeepFold, a deep convolutional neural network model to extract structural motif features of a protein structure. Expand
  • 14
  • 2
...
1
2
3
4
5
...