Make BERT-based Chinese Spelling Check Model Enhanced by Layerwise Attention and Gaussian Mixture Model
This work improves Chinese spelling correction for NLP applications, but it is incremental as it builds on existing BERT-based approaches.
The paper tackled limitations in BERT-based Chinese Spelling Check models by addressing incorrect POS tags from spelling errors and underutilized hierarchical BERT layers, resulting in a performance boost over strong baselines and outperforming previous state-of-the-art methods on two datasets.
BERT-based models have shown a remarkable ability in the Chinese Spelling Check (CSC) task recently. However, traditional BERT-based methods still suffer from two limitations. First, although previous works have identified that explicit prior knowledge like Part-Of-Speech (POS) tagging can benefit in the CSC task, they neglected the fact that spelling errors inherent in CSC data can lead to incorrect tags and therefore mislead models. Additionally, they ignored the correlation between the implicit hierarchical information encoded by BERT's intermediate layers and different linguistic phenomena. This results in sub-optimal accuracy. To alleviate the above two issues, we design a heterogeneous knowledge-infused framework to strengthen BERT-based CSC models. To incorporate explicit POS knowledge, we utilize an auxiliary task strategy driven by Gaussian mixture model. Meanwhile, to incorporate implicit hierarchical linguistic knowledge within the encoder, we propose a novel form of n-gram-based layerwise self-attention to generate a multilayer representation. Experimental results show that our proposed framework yields a stable performance boost over four strong baseline models and outperforms the previous state-of-the-art methods on two datasets.