{"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/densely-connected-bidirectional-lstm-with","title":"Densely Connected Bidirectional LSTM with Applications to Sentence Classification","arxiv_id":"1802.00889","date":"2018-02-03","proceeding":null,"authors":["Zixiang Ding","Rui Xia","Jianfei Yu","Xiang Li","Jian Yang"],"abstract":"Deep neural networks have recently been shown to achieve highly competitive\nperformance in many computer vision tasks due to their abilities of exploring\nin a much larger hypothesis space. However, since most deep architectures like\nstacked RNNs tend to suffer from the vanishing-gradient and overfitting\nproblems, their effects are still understudied in many NLP tasks. Inspired by\nthis, we propose a novel multi-layer RNN model called densely connected\nbidirectional long short-term memory (DC-Bi-LSTM) in this paper, which\nessentially represents each layer by the concatenation of its hidden state and\nall preceding layers' hidden states, followed by recursively passing each\nlayer's representation to all subsequent layers. We evaluate our proposed model\non five benchmark datasets of sentence classification. DC-Bi-LSTM with depth up\nto 20 can be successfully trained and obtain significant improvements over the\ntraditional Bi-LSTM with the same or even less parameters. Moreover, our model\nhas promising performance compared with the state-of-the-art approaches.","url_abs":"http://arxiv.org/abs/1802.00889v1","url_pdf":"http://arxiv.org/pdf/1802.00889v1.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":"densely-connected-bidirectional-lstm-with","repo_url":"https://github.com/kochlisGit/Stocks-Prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"densely-connected-bidirectional-lstm-with","repo_url":"https://github.com/xuhaiming1996/Densely-Connected-Bidirectional-LSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}