@inproceedings{977230331500450285f470eba6686960,
title = "Juman++: A morphological analysis toolkit for scriptio continua",
abstract = "We present a three-part toolkit for developing morphological analyzers for languages without natural word boundaries. The first part is a lattice-based morphological analysis library that uses a combination of linear and recurrent neural net language models for analysis. The other parts are a tool for exposing problems in the trained model and a partial annotation tool. Our morphological analyzer for Japanese achieves new SOTA on Jumandic-based corpora while being 250 times faster than the previous one. We also perform a small experiment and quantitive analysis of using our toolkit.",
author = "Arseny Tolmachev and Daisuke Kawahara and Sadao Kurohashi",
year = "2018",
doi = "10.18653/v1/d18-2010",
language = "English",
series = "EMNLP 2018 - Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "54--59",
booktitle = "EMNLP 2018 - Conference on Empirical Methods in Natural Language Processing",
note = "2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2018 ; Conference date: 31-10-2018 Through 04-11-2018",
}