F
Fuji Ren
Researcher at University of Tokushima
Publications - 622
Citations - 6519
Fuji Ren is an academic researcher from University of Tokushima. The author has contributed to research in topics: Sentence & Machine translation. The author has an hindex of 30, co-authored 579 publications receiving 4966 citations. Previous affiliations of Fuji Ren include Hiroshima City University & Beijing University of Posts and Telecommunications.
Papers
More filters
Proceedings ArticleDOI
Recognizing sentence emotions based on polynomial kernel method using Ren-CECps
Changqin Quan,Fuji Ren +1 more
TL;DR: This study proposes a method of emotion recognition at sentence level based on a relative large emotion annotation corpus (Ren-CECps), and gets the emotion lexicons for the eight basic emotions.
Proceedings ArticleDOI
Human-like facial expression imitation for humanoid robot based on recurrent neural network
Zhong Huang,Fuji Ren,Yanwei Bao +2 more
TL;DR: Compared with the art-of-the-state of methods, the proposed facial motion imitation method not only has smaller expression deviations with the performer, but also keeps smooth servo movements in dynamic facial imitation.
Journal Article
Automatic super-function extraction for translation of spoken dialogue
TL;DR: This paper used a bilingual dictionary to match Japanese and English nouns in each sentence pair in a Japanese-English bilingual corpus to automatically extract super-function (SF) for machine translation.
Journal ArticleDOI
Hybrid Chinese text classification approach using general knowledge from Baidu Baike
TL;DR: The proposed Baidu Baike‐based concept similarity approach obtains promising results when compared with a previous research and the conventional method, and has good expandability, so that many other knowledge bases could be integrated and many other concepts could be referred to improve the effectiveness.
Proceedings ArticleDOI
Dual-chain Unequal-state CRF for Chinese new word detection and POS tagging
Xiao Sun,Fuji Ren,Degen Huang +2 more
TL;DR: The experimental results show that the proposed unified dual-chain unequal-state CRF model is capable of detecting even low frequency new words and their parts-of-speech synchronously with satisfactory results.