H
Hiroyuki Shindo
Researcher at Nara Institute of Science and Technology
Publications - 116
Citations - 2398
Hiroyuki Shindo is an academic researcher from Nara Institute of Science and Technology. The author has contributed to research in topics: Sentence & Parsing. The author has an hindex of 20, co-authored 111 publications receiving 1675 citations. Previous affiliations of Hiroyuki Shindo include Hitachi & Nippon Telegraph and Telephone.
Papers
More filters
Proceedings ArticleDOI
Stochastic Tokenization with a Language Model for Neural Text Classification
TL;DR: This model incorporates a language model for unsupervised tokenization into a text classifier and then trains both models simultaneously, which achieves better performance than previous methods.
Proceedings ArticleDOI
High-accuracy OPC-modeling by using advanced CD-SEM based contours in the next-generation lithography
Daisuke Hibino,Hiroyuki Shindo,Yuichi Abe,Yutaka Hojyo,Germain Fenger,Thuy Do,Ir Kusnadi,John L. Sturtevant,Peter De Bisschop,Jeroen Van de Kerkhove +9 more
TL;DR: The technology of contour alignment and averaging was extended to arbitrary 2D structures and the quality of SEM-contours was significantly improved in cases where the image has both horizontal and vertical edges, by a new SEM image method, which is called 'Fine SEM Edge'.
Journal ArticleDOI
Autoencoder for Semisupervised Multiple Emotion Detection of Conversation Transcripts
TL;DR: A semisupervised multi-label method of predicting emotions from conversation transcripts using an emotion lexicon from the corpus and a deep-learning auto-encoder to discover the underlying structure of the unsupervised data.
Book ChapterDOI
Studio Ousia’s Quiz Bowl Question Answering System
TL;DR: This chapter describes the question answering system, which was the winning system at the Human–Computer Question Answering (HCQA) Competition at the Thirty-first Annual Conference on Neural Information Processing Systems (NIPS).
Journal ArticleDOI
High-accuracy optical proximity correction modeling using advanced critical dimension scanning electron microscope-based contours in next-generation lithography
Daisuke Hibino,Hiroyuki Shindo,Yuichi Abe,Yutaka Hojyo,Germain Fenger,Thuy Do,Ir Kusnadi,John L. Sturtevant,Jeroen Van de Kerkhove,Peter De Bisschop +9 more
TL;DR: The technology of contour alignment and averaging is extended to arbitrary 2-D structures and the quality of scanning electron microscope contours is significantly improved in cases where the image has both horizontal and vertical edges by a new SEM image method, which is called fine SEM edge (FSE).