{"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/long-short-term-memory-with-dynamic-skip","title":"Long Short-Term Memory with Dynamic Skip Connections","arxiv_id":"1811.03873","date":"2018-11-09","proceeding":null,"authors":["Tao Gui","Qi Zhang","Lujun Zhao","Yaosong Lin","Minlong Peng","Jingjing Gong","Xuanjing Huang"],"abstract":"In recent years, long short-term memory (LSTM) has been successfully used to\nmodel sequential data of variable length. However, LSTM can still experience\ndifficulty in capturing long-term dependencies. In this work, we tried to\nalleviate this problem by introducing a dynamic skip connection, which can\nlearn to directly connect two dependent words. Since there is no dependency\ninformation in the training data, we propose a novel reinforcement\nlearning-based method to model the dependency relationship and connect\ndependent words. The proposed model computes the recurrent transition functions\nbased on the skip connections, which provides a dynamic skipping advantage over\nRNNs that always tackle entire sentences sequentially. Our experimental results\non three natural language processing tasks demonstrate that the proposed method\ncan achieve better performance than existing methods. In the number prediction\nexperiment, the proposed model outperformed LSTM with respect to accuracy by\nnearly 20%.","url_abs":"http://arxiv.org/abs/1811.03873v1","url_pdf":"http://arxiv.org/pdf/1811.03873v1.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":"long-short-term-memory-with-dynamic-skip","repo_url":"https://github.com/lecholin/DynamicLSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"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/named-entity-recognition-ner-on-conll-2003","task":"Named Entity Recognition (NER)","dataset":"CoNLL 2003 (English)","model":"LSTM with dynamic skip","rank_in_archive_order":60,"of":73,"metrics":{"F1":"91.56"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"LSTM with dynamic skip","rank_in_archive_order":37,"of":49,"metrics":{"Accuracy":"90.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.03873","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}