• Publications
  • Influence
Gated Self-Matching Networks for Reading Comprehension and Question Answering
The gated self-matching networks for reading comprehension style question answering, which aims to answer questions from a given passage, are presented and holds the first place on the SQuAD leaderboard for both single and ensemble model. Expand
Drug repositioning by integrating target information through a heterogeneous network model
This paper proposes a computational framework based on a heterogeneous network model and applied the approach on drug repositioning by using existing omics data about diseases, drugs and drug targets and shows that the proposed approach significantly outperforms several recent approaches. Expand
Drug Target Predictions Based on Heterogeneous Graph Inference
  • Wenhui Wang, Sen Yang, Jing Li
  • Computer Science, Medicine
  • Pacific Symposium on Biocomputing
  • 1 November 2012
A network based computational approach for novel drug and target association predictions that incorporates known drug-target interactions as well as drug-drug and target-target similarities is proposed and can greatly improve novel target predictions. Expand
Graph-based Dependency Parsing with Bidirectional LSTM
A neural network model for graph-based dependency parsing which utilizes Bidirectional LSTM (BLSTM) to capture richer contextual information instead of using high-order factorization, and enable the model to use much fewer features than previous work. Expand
In Silico Gene Prioritization by Integrating Multiple Data Sources
This paper proposes an expandable framework for gene prioritization that can integrate multiple heterogeneous data sources by taking advantage of a unified graphic representation and shows that this approach consistently outperforms other two state of the art programs. Expand
A Fully Automated Robotic System for Microinjection of Zebrafish Embryos
A microrobotic system for fully automated zebrafish embryo injection is presented, which overcomes the problems inherent in manual operation, such as human fatigue and large variations in success rates due to poor reproducibility. Expand
Multiway Attention Networks for Modeling Sentence Pairs
Experimental results demonstrate that the proposed multiway attention networks improve the result on the Quora Question Pairs, SNLI, MultiNLI, and answer sentence selection task on the SQuAD dataset. Expand
Improved Dependency Parsing using Implicit Word Connections Learned from Unlabeled Data
Experiments show that these implicit word connections do improve the parsing model and by combining with a pre-trained language model, the model gets state-of-the-art performance on the English PTB dataset. Expand
Hand gesture recognition and virtual game control based on 3D accelerometer and EMG sensors
A novel hand gesture recognition system that utilizes both multi-channel surface electromyogram (EMG) sensors and 3D accelerometer (ACC) sensors to realize user-friendly interaction between human and computers is described. Expand
Tapered Optical Fiber Sensor for Label-Free Detection of Biomolecules
A fast, highly sensitive and low-cost tapered optical fiber biosensor that enables the label-free detection of biomolecules and is evaluated with an Immune globulin G (IgG) antibody-antigen pair. Expand