{"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/self-adaptive-hierarchical-sentence-model","title":"Self-Adaptive Hierarchical Sentence Model","arxiv_id":"1504.05070","date":"2015-04-20","proceeding":null,"authors":["Han Zhao","Zhengdong Lu","Pascal Poupart"],"abstract":"The ability to accurately model a sentence at varying stages (e.g.,\nword-phrase-sentence) plays a central role in natural language processing. As\nan effort towards this goal we propose a self-adaptive hierarchical sentence\nmodel (AdaSent). AdaSent effectively forms a hierarchy of representations from\nwords to phrases and then to sentences through recursive gated local\ncomposition of adjacent segments. We design a competitive mechanism (through\ngating networks) to allow the representations of the same sentence to be\nengaged in a particular learning task (e.g., classification), therefore\neffectively mitigating the gradient vanishing problem persistent in other\nrecursive models. Both qualitative and quantitative analysis shows that AdaSent\ncan automatically form and select the representations suitable for the task at\nhand during training, yielding superior classification performance over\ncompetitor models on 5 benchmark data sets.","url_abs":"http://arxiv.org/abs/1504.05070v2","url_pdf":"http://arxiv.org/pdf/1504.05070v2.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":"self-adaptive-hierarchical-sentence-model","repo_url":"https://bitbucket.org/taoyds/nbsvm_pos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"subjectivity-analysis","task_name":"Subjectivity Analysis"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/subjectivity-analysis-on-subj","task":"Subjectivity Analysis","dataset":"SUBJ","model":"AdaSent","rank_in_archive_order":5,"of":19,"metrics":{"Accuracy":"95.50"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1504.05070","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}