Toward Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning
This work addresses the challenge of dataset divergence in CWS for NLP applications, offering a more accurate and efficient solution, though it is incremental as it builds on existing BERT-based methods.
The paper tackled the problem of ambiguous annotation criteria in Chinese Word Segmentation (CWS) by proposing a domain adaptive segmenter that leverages multi-criteria learning, resulting in outperforming previous state-of-the-art models on 10 CWS datasets with improved efficiency.
The ambiguous annotation criteria lead to divergence of Chinese Word Segmentation (CWS) datasets in various granularities. Multi-criteria Chinese word segmentation aims to capture various annotation criteria among datasets and leverage their common underlying knowledge. In this paper, we propose a domain adaptive segmenter to exploit diverse criteria of various datasets. Our model is based on Bidirectional Encoder Representations from Transformers (BERT), which is responsible for introducing open-domain knowledge. Private and shared projection layers are proposed to capture domain-specific knowledge and common knowledge, respectively. We also optimize computational efficiency via distillation, quantization, and compiler optimization. Experiments show that our segmenter outperforms the previous state of the art (SOTA) models on 10 CWS datasets with superior efficiency.