{"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/learning-to-embed-sentences-using-attentive","title":"Learning to Embed Sentences Using Attentive Recursive Trees","arxiv_id":"1811.02338","date":"2018-11-06","proceeding":null,"authors":["Jiaxin Shi","Lei Hou","Juanzi Li","Zhiyuan Liu","Hanwang Zhang"],"abstract":"Sentence embedding is an effective feature representation for most deep\nlearning-based NLP tasks. One prevailing line of methods is using recursive\nlatent tree-structured networks to embed sentences with task-specific\nstructures. However, existing models have no explicit mechanism to emphasize\ntask-informative words in the tree structure. To this end, we propose an\nAttentive Recursive Tree model (AR-Tree), where the words are dynamically\nlocated according to their importance in the task. Specifically, we construct\nthe latent tree for a sentence in a proposed important-first strategy, and\nplace more attentive words nearer to the root; thus, AR-Tree can inherently\nemphasize important words during the bottom-up composition of the sentence\nembedding. We propose an end-to-end reinforced training strategy for AR-Tree,\nwhich is demonstrated to consistently outperform, or be at least comparable to,\nthe state-of-the-art sentence embedding methods on three sentence understanding\ntasks.","url_abs":"http://arxiv.org/abs/1811.02338v2","url_pdf":"http://arxiv.org/pdf/1811.02338v2.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":"learning-to-embed-sentences-using-attentive","repo_url":"https://github.com/shijx12/AR-Tree","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-embed-sentences-using-attentive","repo_url":"https://github.com/shijx12/shijx12.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}