Back to Patterns: Efficient Japanese Morphological Analysis with Feature-Sequence Trie
This provides a highly efficient solution for processing large-scale social media data or real-time queries in Japanese NLP, though it is incremental as it builds on existing pattern-based approaches.
The study tackled the inefficiency of neural models for Japanese morphological analysis by revisiting pattern-based methods, achieving comparable accuracy to learning-based baselines with a throughput of over 1,000,000 sentences per second on a single CPU.
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 https://www.tkl.iis.u-tokyo.ac.jp/~ynaga/jagger/