{"ID":2827364,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16125","arxiv_id":"2512.16125","title":"Convolutional Lie Operator for Sentence Classification","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.16125","url_pdf":"https://arxiv.org/pdf/2512.16125v1","authors":"[\"Daniela N. Rim\",\"Heeyoul Choi\"]","published":"2025-12-18T03:23:37Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false}