Deep Learning for Classical Japanese Literature
Abstract
Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance. In this work, we introduce Kuzushiji-MNIST, a dataset which focuses on Kuzushiji (cursive Japanese), as well as two larger, more challenging datasets, Kuzushiji-49 and Kuzushiji-Kanji. Through these datasets, we wish to engage the machine learning community into the world of classical Japanese literature. Dataset available at https://github.com/rois-codh/kmnist
Cite
@article{arxiv.1812.01718,
title = {Deep Learning for Classical Japanese Literature},
author = {Tarin Clanuwat and Mikel Bober-Irizar and Asanobu Kitamoto and Alex Lamb and Kazuaki Yamamoto and David Ha},
journal= {arXiv preprint arXiv:1812.01718},
year = {2018}
}
Comments
To appear at Neural Information Processing Systems 2018 Workshop on Machine Learning for Creativity and Design