Zobrazeno 1 - 10
of 73
pro vyhledávání: '"Shimbo, Masashi"'
We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this paper, we d
Externí odkaz:
http://arxiv.org/abs/2403.08174
Publikováno v:
Pattern Recognition Letters 173 (2023) 93-100
The Meta Video Dataset (MetaVD) provides annotated relations between action classes in major datasets for human action recognition in videos. Although these annotated relations enable dataset augmentation, it is only applicable to those covered by Me
Externí odkaz:
http://arxiv.org/abs/2308.07558
Barlow Twins and VICReg are self-supervised representation learning models that use regularizers to decorrelate features. Although these models are as effective as conventional representation learning models, their training can be computationally dem
Externí odkaz:
http://arxiv.org/abs/2301.01569
For knowledge graph completion, two major types of prediction models exist: one based on graph embeddings, and the other based on relation path rule induction. They have different advantages and disadvantages. To take advantage of both types, hybrid
Externí odkaz:
http://arxiv.org/abs/2111.00974
Methods based on vector embeddings of knowledge graphs have been actively pursued as a promising approach to knowledge graph completion.However, embedding models generate storage-inefficient representations, particularly when the number of entities a
Externí odkaz:
http://arxiv.org/abs/1912.02686
Autor:
Hayashi, Katsuhiko, Shimbo, Masashi
Bilinear diagonal models for knowledge graph embedding (KGE), such as DistMult and ComplEx, balance expressiveness and computational efficiency by representing relations as diagonal matrices. Although they perform well in predicting atomic relations,
Externí odkaz:
http://arxiv.org/abs/1909.01567
Tensor factorization has become an increasingly popular approach to knowledge graph completion(KGC), which is the task of automatically predicting missing facts in a knowledge graph. However, even with a simple model like CANDECOMP/PARAFAC(CP) tensor
Externí odkaz:
http://arxiv.org/abs/1902.02970
Embedding-based methods for knowledge base completion (KBC) learn representations of entities and relations in a vector space, along with the scoring function to estimate the likelihood of relations between entities. The learnable class of scoring fu
Externí odkaz:
http://arxiv.org/abs/1808.08361
This paper proposes an inexpensive way to learn an effective dissimilarity function to be used for $k$-nearest neighbor ($k$-NN) classification. Unlike Mahalanobis metric learning methods that map both query (unlabeled) objects and labeled objects to
Externí odkaz:
http://arxiv.org/abs/1806.03945
Knowledge base completion (KBC) aims to predict missing information in a knowledge base.In this paper, we address the out-of-knowledge-base (OOKB) entity problem in KBC:how to answer queries concerning test entities not observed at training time. Exi
Externí odkaz:
http://arxiv.org/abs/1706.05674