Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Chen, Huajun"'
Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance. Existing solutions usually address this issue via class-balancing strategi
Externí odkaz:
http://arxiv.org/abs/2009.07022
Link prediction is an important way to complete knowledge graphs (KGs), while embedding-based methods, effective for link prediction in KGs, perform poorly on relations that only have a few associative triples. In this work, we propose a Meta Relatio
Externí odkaz:
http://arxiv.org/abs/1909.01515
Relation extraction aims to extract relational facts from sentences. Previous models mainly rely on manually labeled datasets, seed instances or human-crafted patterns, and distant supervision. However, the human annotation is expensive, while human-
Externí odkaz:
http://arxiv.org/abs/1908.08507
Publikováno v:
IJCAI 2019
Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment transfer l
Externí odkaz:
http://arxiv.org/abs/1905.13672
Transfer learning which aims at utilizing knowledge learned from one problem (source domain) to solve another different but related problem (target domain) has attracted wide research attentions. However, the current transfer learning methods are mos
Externí odkaz:
http://arxiv.org/abs/1901.08547