@inproceedings{yoshinaga-2023-back,
title = "Back to Patterns: Efficient {J}apanese Morphological Analysis with Feature-Sequence Trie",
author = "Yoshinaga, Naoki",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.2",
doi = "10.18653/v1/2023.acl-short.2",
pages = "13--23",
abstract = "Accurate neural models are much less efficient than non-neural models and are useless for processing billions of social media posts or handling user queries in real time with a limited budget. This study revisits the fastest pattern-based NLP methods to make them as accurate as possible, thus yielding a strikingly simple yet surprisingly accurate morphological analyzer for Japanese. The proposed method induces reliable patterns from a morphological dictionary and annotated data. Experimental results on two standard datasets confirm that the method exhibits comparable accuracy to learning-based baselines, while boasting a remarkable throughput of over 1,000,000 sentences per second on a single modern CPU. The source code is available at \url{https://www.tkl.iis.u-tokyo.ac.jp/ynaga/jagger/}",
}
Markdown (Informal)
[Back to Patterns: Efficient Japanese Morphological Analysis with Feature-Sequence Trie](https://aclanthology.org/2023.acl-short.2) (Yoshinaga, ACL 2023)
ACL