Multi-Level Cross-Lingual Transfer Learning With Language Shared and Specific Knowledge for Spoken Language Understanding

Recently conversational agents effectively improve their understanding capabilities by neural networks.Such deep neural models, however, do not apply to most human languages due to the lack of annotated training data for various NLP tasks.In this paper, we propose a multi-level cross-lingual transfer model with language shared and specific knowledg

read more




Irrational Responses to Risk Preference Questionnaires by Patients with Diabetes with or without Retinopathy and Comparison with Those without Diabetes

Naoya Emoto,1,2 Akimi Soga,1 Izumi Fukuda,1 Kyoko Tanimura-Inagaki,1 Taro Harada,1 Hajime M Koyano,3 Rei Goto,4 Hitoshi Sugihara1 1Department of Endocrinology, Diabetes and Metabolism, Graduate School of Medicine, Nippon Medical School, Tokyo, Japan; 2Diabetes & Thyroid Clinic, Sakura Chuo Hospital, Chiba, Japan; 3Division of Endocrinology and

read more