用李群卷积提升句子分类，捕捉语言中复杂变换模式。
Convolutional Lie Operator for Sentence Classification
- 将李群卷积引入文本分类，建模非欧几里得对称变换
- 在多个数据集上优于传统CNN模型，提升分类准确率
- 适合对语言结构建模、新范式探索的研究者
传统卷积神经网络在捕捉文本局部、位置无关特征方面表现良好，但对语言内部复杂变换的建模能力仍有提升空间。本文受李群运算能捕捉复杂非欧几里得对称性的启发，提出SCLie与DPCLie两种基于李卷积的句子分类模型。实验表明，这些模型在多个基准数据集上显著优于传统卷积分类器，验证了李群机制在建模语言中不常见变换模式方面的有效性。研究结果推动了语言建模中新范式的探索。
原文摘要 · Abstract (English)
Traditional Convolutional Neural Networks have been successful in capturing local, position-invariant features in text, but their capacity to model complex transformation within language can be further explored. In this work, we explore a novel approach by integrating Lie Convolutions into Convolutional-based sentence classifiers, inspired by the ability of Lie group operations to capture complex, non-Euclidean symmetries. Our proposed models SCLie and DPCLie empirically outperform traditional Convolutional-based sentence classifiers, suggesting that Lie-based models relatively improve the accuracy by capturing transformations not commonly associated with language. Our findings motivate more exploration of new paradigms in language modeling.
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。