AxBERT: An Interpretable Chinese Spelling Correction Method Driven by Associative Knowledge Network
Wang, Fanyu, Zhu, Hangyu, Xie, Zhenping
–arXiv.org Artificial Intelligence
Deep learning has shown promising performance on various machine learning tasks. Nevertheless, the uninterpretability of deep learning models severely restricts the usage domains that require feature explanations, such as text correction. Therefore, a novel interpretable deep learning model (named AxBERT) is proposed for Chinese spelling correction by aligning with an associative knowledge network (AKN). Wherein AKN is constructed based on the co-occurrence relations among Chinese characters, which denotes the interpretable statistic logic contrasted with uninterpretable BERT logic. And a translator matrix between BERT and AKN is introduced for the alignment and regulation of the attention component in BERT. In addition, a weight regulator is designed to adjust the attention distributions in BERT to appropriately model the sentence semantics. Experimental results on SIGHAN datasets demonstrate that AxBERT can achieve extraordinary performance, especially upon model precision compared to baselines. Our interpretable analysis, together with qualitative reasoning, can effectively illustrate the interpretability of AxBERT.
arXiv.org Artificial Intelligence
Mar-3-2025
- Country:
- North America
- Canada (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- New York > New York County
- New York City (0.04)
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Washington > King County
- Europe
- France (0.04)
- Spain
- Valencian Community > Valencia Province
- Valencia (0.04)
- Catalonia > Barcelona Province
- Barcelona (0.04)
- Valencian Community > Valencia Province
- Italy > Tuscany
- Florence (0.05)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia > China
- Jiangsu Province (0.14)
- Hong Kong (0.04)
- Hubei Province > Wuhan (0.04)
- Beijing > Beijing (0.04)
- North America
- Genre:
- Overview (0.93)
- Research Report (0.82)
- Technology: