A BiLSTM-CRF Based Approach to Word Segmentation in Chinese
Yuanyuan Jin, Shiyu Tao, Qi Liu, Xiaodong Liu · 2022 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · 2022
This paper proposes a approach for word segmentation in Chinese. The word segmentation model in this paper combines Bi-directional Long Short-Term Memory (BiLSTM) and Conditional Random Fields (CRF), and proposes a four-state word segmentation model of DSZM, so that the model can not only consider the correlation between the front and rear of the sequence like CRF, but also have the feature extraction and fitting capabilities of BiLSTM.