{"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/compositional-distributional-semantics-with","title":"Compositional Distributional Semantics with Long Short Term Memory","arxiv_id":"1503.02510","date":"2015-03-09","proceeding":"SEMEVAL 2015 6","authors":["Phong Le","Willem Zuidema"],"abstract":"We are proposing an extension of the recursive neural network that makes use\nof a variant of the long short-term memory architecture. The extension allows\ninformation low in parse trees to be stored in a memory register (the `memory\ncell') and used much later higher up in the parse tree. This provides a\nsolution to the vanishing gradient problem and allows the network to capture\nlong range dependencies. Experimental results show that our composition\noutperformed the traditional neural-network composition on the Stanford\nSentiment Treebank.","url_abs":"http://arxiv.org/abs/1503.02510v2","url_pdf":"http://arxiv.org/pdf/1503.02510v2.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":"compositional-distributional-semantics-with","repo_url":"https://github.com/lephong/lstm-rnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1503.02510","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}