Sonse Shimaoka

Learn More
In this work we propose a novel attentionbased neural network model for the task of fine-grained entity type classification that unlike previously proposed models recursively composes representations of entity mention contexts. Our model achieves state-of-theart performance with 74.94% loose micro F1score on the well-established FIGER dataset, a relative(More)
Topical vitamin D3 has relatively recently been introduced for the treatment of psoriasis. Synthetic vitamin D3 analogues with a high potential for inducing differentiation of cells, but with a low hypercalcemic effect have recently been developed. One such synthetic analogue of 1,25-dihydroxyvitamin D3 (calcitriol), 22-oxacalcitriol (OCT), is a novel agent(More)
DNA synthesis of adult rat parenchymal hepatocytes alone in primary culture can be stimulated only by the addition of humoral growth factors to the culture medium. However, when parenchymal hepatocytes were cocultured with nonparenchymal liver cells from adult rats, their DNA synthesis was markedly stimulated in the absence of added growth factors or calf(More)
In this work, we investigate several neural network architectures for fine-grained entity type classification. Particularly, we consider extensions to a recently proposed attentive neural architecture and make three key contributions. Previous work on attentive neural architectures do not consider hand-crafted features, we combine learnt and hand-crafted(More)
The field of distributional-compositional semantics has yielded a range of computational models for composing the vector of a phrase from those of constituent word vectors. Existing models have various ranges of their expressiveness, recursivity, and trainability. However, these models have not been examined closely for their compositionality. We implement(More)
  • 1