{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/convolutional-neural-networks-with-recurrent","title":"Convolutional Neural Networks with Recurrent Neural Filters","arxiv_id":"1808.09315","date":"2018-08-28","proceeding":"EMNLP 2018 10","authors":["Yi Yang"],"abstract":"We introduce a class of convolutional neural networks (CNNs) that utilize\nrecurrent neural networks (RNNs) as convolution filters. A convolution filter\nis typically implemented as a linear affine transformation followed by a\nnon-linear function, which fails to account for language compositionality. As a\nresult, it limits the use of high-order filters that are often warranted for\nnatural language processing tasks. In this work, we model convolution filters\nwith RNNs that naturally capture compositionality and long-term dependencies in\nlanguage. We show that simple CNN architectures equipped with recurrent neural\nfilters (RNFs) achieve results that are on par with the best published ones on\nthe Stanford Sentiment Treebank and two answer sentence selection datasets.","url_abs":"http://arxiv.org/abs/1808.09315v1","url_pdf":"http://arxiv.org/pdf/1808.09315v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"convolutional-neural-networks-with-recurrent","repo_url":"https://github.com/bloomberg/cnn-rnf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"convolutional-neural-networks-with-recurrent","repo_url":"https://github.com/davide97l/Sentiment-analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"CNN-RNF-LSTM","rank_in_archive_order":62,"of":87,"metrics":{"Accuracy":"90.0"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-5-fine-grained","task":"Sentiment Analysis","dataset":"SST-5 Fine-grained classification","model":"CNN-RNF-LSTM","rank_in_archive_order":12,"of":31,"metrics":{"Accuracy":"53.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}