{"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/a-c-lstm-neural-network-for-text","title":"A C-LSTM Neural Network for Text Classification","arxiv_id":"1511.08630","date":"2015-11-27","proceeding":null,"authors":["Chunting Zhou","Chonglin Sun","Zhiyuan Liu","Francis C. M. Lau"],"abstract":"Neural network models have been demonstrated to be capable of achieving\nremarkable performance in sentence and document modeling. Convolutional neural\nnetwork (CNN) and recurrent neural network (RNN) are two mainstream\narchitectures for such modeling tasks, which adopt totally different ways of\nunderstanding natural languages. In this work, we combine the strengths of both\narchitectures and propose a novel and unified model called C-LSTM for sentence\nrepresentation and text classification. C-LSTM utilizes CNN to extract a\nsequence of higher-level phrase representations, and are fed into a long\nshort-term memory recurrent neural network (LSTM) to obtain the sentence\nrepresentation. C-LSTM is able to capture both local features of phrases as\nwell as global and temporal sentence semantics. We evaluate the proposed\narchitecture on sentiment classification and question classification tasks. The\nexperimental results show that the C-LSTM outperforms both CNN and LSTM and can\nachieve excellent performance on these tasks.","url_abs":"http://arxiv.org/abs/1511.08630v2","url_pdf":"http://arxiv.org/pdf/1511.08630v2.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":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/EngSalem/ArabicTextClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/EngSalem/Text-Classification-of-the-shelf-with-a-normalizer-for-Arabic-text-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/EngSalem/TextClassification_Off_the_shelf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/KifayatMsd/C-LSTM-text-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/ManuelVs/NNForTextClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/ManuelVs/NeuralNetworks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/MingyuLi19910814/C-LSTM-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/jingyuanz/telecom_query_classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/shamalwinchurkar/question-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-c-lstm-neural-network-for-text","repo_url":"https://github.com/zackhy/TextClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"C-LSTM","rank_in_archive_order":69,"of":87,"metrics":{"Accuracy":"87.8"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-5-fine-grained","task":"Sentiment Analysis","dataset":"SST-5 Fine-grained classification","model":"C-LSTM","rank_in_archive_order":22,"of":31,"metrics":{"Accuracy":"49.2"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-trec-6","task":"Text Classification","dataset":"TREC-6","model":"C-LSTM","rank_in_archive_order":10,"of":19,"metrics":{"Error":"5.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.08630","atlas_url":"https://app.syntology.ai/?focus=1511.08630","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}