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 this https URL
| Comments: | 9 pages, 1 figure, 10 tables, Accepted by ACL 2023 (main conference) |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2305.19045 [cs.CL] |
| (or arXiv:2305.19045v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2305.19045 arXiv-issued DOI via DataCite |
Submission history
From: Naoki Yoshinaga [view email]
[v1]
Tue, 30 May 2023 14:00:30 UTC (150 KB)