C
Carl Allen
Researcher at University of Edinburgh
Publications - 22
Citations - 1856
Carl Allen is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Word2vec & Embedding. The author has an hindex of 12, co-authored 21 publications receiving 940 citations. Previous affiliations of Carl Allen include University of Southampton.
Papers
More filters
Proceedings ArticleDOI
TuckER: Tensor Factorization for Knowledge Graph Completion.
TL;DR: This paper proposed TuckER, a linear model based on Tucker decomposition of the binary tensor representation of knowledge graph triples, which outperforms previous state-of-the-art models across standard link prediction datasets.
Posted Content
Multi-scale Attributed Node Embedding
TL;DR: It is proved theoretically that matrices of node-feature pointwise mutual information are implicitly factorized by the embeddings, and computationally efficient and outperform comparable models on social networks and web graphs.
Proceedings Article
Multi-relational Poincaré Graph Embeddings
TL;DR: The Multi-Relational Poincare model (MuRP) learns relation-specific parameters to transform entity embeddings by Mobius matrix-vector multiplication and Mobius addition and outperform their Euclidean counterpart and existing embedding methods on the link prediction task, particularly at lower dimensionality.
Proceedings ArticleDOI
TuckER: Tensor Factorization for Knowledge Graph Completion.
TL;DR: The authors proposed TuckER, a linear model based on Tucker decomposition of the binary tensor representation of knowledge graph triples, which outperforms previous state-of-the-art models across standard link prediction datasets.
Book ChapterDOI
Hypernetwork Knowledge Graph Embeddings
TL;DR: It is demonstrated that convolution simply offers a convenient computational means of introducing sparsity and parameter tying to find an effective trade-off between non-linear expressiveness and the number of parameters to learn.