W
Wei Hu
Researcher at Nanjing University
Publications - 88
Citations - 3885
Wei Hu is an academic researcher from Nanjing University. The author has contributed to research in topics: Ontology alignment & Semantic Web. The author has an hindex of 24, co-authored 86 publications receiving 2735 citations. Previous affiliations of Wei Hu include Southeast University.
Papers
More filters
Proceedings ArticleDOI
Bootstrapping Entity Alignment with Knowledge Graph Embedding
TL;DR: A bootstrapping approach to embedding-based entity alignment that iteratively labels likely entity alignment as training data for learning alignment-oriented KG embeddings and employs an alignment editing method to reduce error accumulation during iterations.
Book ChapterDOI
Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding
Zequn Sun,Wei Hu,Chengkai Li +2 more
TL;DR: This paper propose a joint attribute-preserving embedding model for cross-lingual entity alignment, which jointly embeds the structures of two knowledge bases into a unified vector space and further refines it by leveraging attribute correlations in the knowledge bases.
Journal ArticleDOI
Matching large ontologies: A divide-and-conquer approach
Wei Hu,Yuzhong Qu,Gong Cheng +2 more
TL;DR: A structure-based partitioning algorithm, which partitions entities of each ontology into a set of small clusters and constructs blocks by assigning RDF Sentences to those clusters, and two powerful matchers, V-Doc and Gmo, are employed to discover alignments in the block mappings.
Journal ArticleDOI
Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
TL;DR: AliNet as discussed by the authors introduces distant neighbors to expand the overlap between their neighborhood structures, and employs an attention mechanism to highlight helpful distant neighbors and reduce noises, and then it controls the aggregation of both direct and distant neighborhood information using a gating mechanism.
Journal ArticleDOI
Falcon-AO: A practical ontology matching system
Wei Hu,Yuzhong Qu +1 more
TL;DR: An overview of Falcon-AO: a practical ontology matching system with acceptable to good performance and a number of remarkable features that is one of the best systems in all kinds of tests in the latest three years' OAEI campaigns.