Convolutional Neural Networks with Recurrent Neural Filters
This addresses the problem of improving natural language processing tasks for researchers and practitioners by offering a novel filter design, though it appears incremental as it builds on existing CNN architectures.
The paper tackled the limitation of standard CNN filters in capturing language compositionality by introducing recurrent neural filters (RNFs) that use RNNs to model convolution filters, achieving results on par with the best published ones on the Stanford Sentiment Treebank and two answer sentence selection datasets.
We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters. A convolution filter is typically implemented as a linear affine transformation followed by a non-linear function, which fails to account for language compositionality. As a result, it limits the use of high-order filters that are often warranted for natural language processing tasks. In this work, we model convolution filters with RNNs that naturally capture compositionality and long-term dependencies in language. We show that simple CNN architectures equipped with recurrent neural filters (RNFs) achieve results that are on par with the best published ones on the Stanford Sentiment Treebank and two answer sentence selection datasets.