用关联知识网络提升中文纠错可解释性
AxBERT: An Interpretable Chinese Spelling Correction Method Driven by Associative Knowledge Network
- 基于汉字共现关系构建可解释的关联知识网络
- 通过翻译矩阵对齐BERT注意力机制，提升纠错精度
- 适合需要可解释性的文本修正场景，如教育与法律
深度学习在各类机器学习任务中表现优异，但其不可解释性严重限制了需特征解释的应用领域，如文本校正。为此，本文提出一种新型可解释深度学习模型AxBERT，通过与关联知识网络（AKN）对齐实现中文拼写纠错。AKN基于汉字共现关系构建，体现可解释的统计逻辑，与BERT的不可解释逻辑形成对比。引入BERT与AKN间的翻译矩阵，以对齐和调控BERT的注意力组件；同时设计权重调节器，调整BERT的注意力分布以更准确建模句子语义。在SIGHAN数据集上的实验表明，AxBERT在纠错性能上显著优于基线模型，尤其在模型精确率方面表现突出。可解释性分析与定性推理有效验证了AxBERT的可解释性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。