State-of-the-art Chinese Word Segmentation with Bi-LSTMs
This work addresses segmentation accuracy for Chinese language processing, but it is incremental as it applies existing methods to improve performance.
The paper tackled Chinese word segmentation by showing that a bidirectional LSTM model with standard deep learning techniques achieves better accuracy on popular datasets compared to more complex neural architectures, with concrete improvements noted.
A wide variety of neural-network architectures have been proposed for the task of Chinese word segmentation. Surprisingly, we find that a bidirectional LSTM model, when combined with standard deep learning techniques and best practices, can achieve better accuracy on many of the popular datasets as compared to models based on more complex neural-network architectures. Furthermore, our error analysis shows that out-of-vocabulary words remain challenging for neural-network models, and many of the remaining errors are unlikely to be fixed through architecture changes. Instead, more effort should be made on exploring resources for further improvement.