K
Kun Xu
Researcher at Beijing University of Posts and Telecommunications
Publications - 656
Citations - 8643
Kun Xu is an academic researcher from Beijing University of Posts and Telecommunications. The author has contributed to research in topics: Computer science & Photonics. The author has an hindex of 42, co-authored 580 publications receiving 6499 citations. Previous affiliations of Kun Xu include IBM & Nanjing Medical University.
Papers
More filters
Journal ArticleDOI
Significantly enhanced energy storage performance promoted by ultimate sized ferroelectric BaTiO3 fillers in nanocomposite films
Yanan Hao,Xiaohui Wang,Ke Bi,Jiameng Zhang,Yunhui Huang,Longwen Wu,Peiyao Zhao,Kun Xu,Ming Lei,Longtu Li +9 more
TL;DR: In this article, the effect of nanoparticle fraction on the microstructure and dielectric properties of composite films is investigated, which confirms that these ultimate sized nanocrystals can perform as superior high permittivity fillers in the nanocomposites for energy storage applications.
Proceedings ArticleDOI
Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
TL;DR: This paper proposes to learn more robust relation representations from shortest dependency paths through a convolution neural network, takes the relation directionality into account and proposes a straightforward negative sampling strategy to improve the assignment of subjects and objects.
Proceedings ArticleDOI
Question Answering on Freebase via Relation Extraction and Textual Evidence
TL;DR: The authors used a neural network based relation extractor to retrieve candidate answers from Freebase, and then infer over Wikipedia to validate these answers, achieving an F_1 of 53.3% on the WebQuestions question answering dataset.
Proceedings ArticleDOI
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
TL;DR: The topic entity graph is introduced, a local sub-graph of an entity, to represent entities with their contextual information in KG, and a graph-attention based solution is proposed that outperforms previous state-of-the-art methods by a large margin.