Fast Neural Chinese Word Segmentation for Long Sentences
This addresses a speed bottleneck for researchers and practitioners in natural language processing, though it is incremental as it builds on existing neural approaches.
The paper tackles the computational inefficiency of neural Chinese word segmentation for long sentences by introducing a simple, fully end-to-end segmenter that labels gaps between characters, achieving comparable performance to state-of-the-art methods.
Rapidly developed neural models have achieved competitive performance in Chinese word segmentation (CWS) as their traditional counterparts. However, most of methods encounter the computational inefficiency especially for long sentences because of the increasing model complexity and slower decoders. This paper presents a simple neural segmenter which directly labels the gap existence between adjacent characters to alleviate the existing drawback. Our segmenter is fully end-to-end and capable of performing segmentation very fast. We also show a performance difference with different tag sets. The experiments show that our segmenter can provide comparable performance with state-of-the-art.