HREB-CRF: Hierarchical Reduced-bias EMA for Chinese Named Entity Recognition
It addresses a domain-specific problem for Chinese NLP practitioners, offering incremental improvements over existing methods.
The paper tackled errors in Chinese Named Entity Recognition caused by boundary division, semantic complexity, and pronunciation differences by proposing the HREB-CRF framework, which improved F1 scores by 1.1%, 1.6%, and 9.8% on MSRA, Resume, and Weibo datasets.
Incorrect boundary division, complex semantic representation, and differences in pronunciation and meaning often lead to errors in Chinese Named Entity Recognition(CNER). To address these issues, this paper proposes HREB-CRF framework: Hierarchical Reduced-bias EMA with CRF. The proposed method amplifies word boundaries and pools long text gradients through exponentially fixed-bias weighted average of local and global hierarchical attention. Experimental results on the MSRA, Resume, and Weibo datasets show excellent in F1, outperforming the baseline model by 1.1\%, 1.6\%, and 9.8\%. The significant improvement in F1 shows evidences of strong effectiveness and robustness of approach in CNER tasks.