- Day 1 (Nov.17), 10:00-12:30
- Room 1101 (11th floor)
- Speakers: Yoshimasa Tsuruoka (University of Tokyo), Yoshitaka Ushiku (OMRON SINIC X)
Abstract (Yoshimasa Tsuruoka)
The field of natural language processing (NLP) has witnessed major advancements in recent years thanks to deep learning technology. The accuracy of basic NLP tasks has improved drastically and the high-level tasks that were formerly possible only through complex combination of customized algorithms are now possible via end-to-end learning with relatively simple neural network architectures. This tutorial will cover the basics of deep learning-based NLP and some representative NLP applications including machine translation, summarization and question answering. It will also cover some recent research efforts for building NLP systems in resource-poor settings, such as unsupervised neural machine translation and large-scale pretraining and adaptation of deep learning models.
Biography (Yoshimasa Tsuruoka)
Yoshimasa Tsuruoka is a professor at the University of Tokyo in the Department of Information and Communication Engineering. He has been working on natural language processing for about 20 years and developed various algorithms for low-level language processing such as tagging and parsing as well as high-level applications such as text mining and machine translation. His recent research interests include deep learning-based natural language processing, reinforcement learning and artificial intelligence for games.
Abstract (Yoshitaka Ushiku)
In 2012, computer vision (CV) benefited from deep learning, resulting in dramatic improvements in image recognition performance. Various applications such as detection and segmentation as well as research of 3D vision are widely studied. CV has also been a testbed for fundamental machine learning technologies such as domain adaptation. Besides, with the development of recent machine learning techniques and the commoditization of them, integrating different modalities such as vision and language is spreading widely. In this talk, I will introduce some challenging tasks in CV and some additional topics in vision and language.
Biography (Yoshitaka Ushiku)
Yoshitaka Ushiku is a Principal Investigator at OMRON SINIC X Corporation. He received his B.E., M.A., and Ph.D. degrees from the University of Tokyo in 2009, 2011, and 2014, respectively. In 2014, he joined NTT CS Labs, Japan, where he was involved in research on image recognition. From 2016 to 2018, he was a lecturer with the University of Tokyo, Japan. His research interests lie in computer vision and natural language processing, with a particular interest in vision and language topics such as image captioning and visual question answering.