Convolutional Lie Operator for Sentence Classification
This work addresses the need for better sentence classification models by introducing a novel approach, though it appears incremental as it builds on existing convolutional methods.
The paper tackled the problem of modeling complex transformations in language for sentence classification by integrating Lie convolutions into convolutional neural networks, resulting in models SCLie and DPCLie that empirically outperform traditional convolutional-based classifiers with relative accuracy improvements.
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.