• Publications
  • Influence
Collective entity linking in web text: a graph-based method
TLDR
This paper proposes a graph-based collective EL method, which can model and exploit the global interdependence between different EL decisions. Expand
  • 368
  • 39
  • PDF
Learning to Bootstrap for Entity Set Expansion
TLDR
We propose a novel bootstrapping method combining the Monte Carlo Tree Search (MCTS) algorithm with a deep similarity network, which can efficiently estimate delayed feedback for pattern evaluation and adaptively score entities given sparse supervision. Expand
  • 6
  • 3
  • PDF
Nimodipine nanocrystals for oral bioavailability improvement: preparation, characterization and pharmacokinetic studies.
  • Qiang Fu, J. Sun, +13 authors Z. He
  • Chemistry, Medicine
  • Colloids and surfaces. B, Biointerfaces
  • 1 September 2013
This study intended to develop nimodipine (NMD) nanocrystals with different sizes for oral administration and to investigate the relationship between dissolution and pharmacokinetics for NMDExpand
  • 52
  • 2
Deep Sequence-to-Sequence Entity Matching for Heterogeneous Entity Resolution
TLDR
We propose an align-compare-aggregate neural network for Seq2Seq entity matching, which can learn representations of tokens, capture the semantic relevance between tokens, and aggregate matching evidence for accurate ER decisions in an end-to-end manner. Expand
  • 13
  • 1
Stator-PM-Based Variable Reluctance Resolver With Advantage of Motional Back-EMF
TLDR
This article proposes a novel structure for a variable reluctance (VR) resolver by using the concept of the stator PM. Expand
  • 5
  • 1
Hierarchical Matching Network for Heterogeneous Entity Resolution
TLDR
We propose an end-to-end hierarchical matching network (HierMatcher) for entity resolution that can jointly match entities in three levels—token, attribute, and entity. Expand
  • 4
  • 1
  • PDF
ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling
TLDR
We propose a transformers-based system which is based on pre-trained transformers for detecting counterfactual statements. Expand
  • 1
  • 1
  • PDF
An Advanced Two-Step DNN-Based Framework for Arrhythmia Detection
TLDR
This paper presents a two-step DNN-based framework to identify arrhythmia-related heartbeats. Expand
  • 1
  • 1
  • PDF
Low Rank Component Induced Spatial-Spectral Kernel Method for Hyperspectral Image Classification
TLDR
We propose a novel patch-based low rank component induced spatial-spectral kernel method, termed LRCISSK, for HSI classification. Expand
  • 22