{"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/dynamic-compositionality-in-recursive-neural","title":"Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations","arxiv_id":"1809.02286","date":"2018-09-07","proceeding":null,"authors":["Taeuk Kim","Jihun Choi","Daniel Edmiston","Sanghwan Bae","Sang-goo Lee"],"abstract":"Most existing recursive neural network (RvNN) architectures utilize only the\nstructure of parse trees, ignoring syntactic tags which are provided as\nby-products of parsing. We present a novel RvNN architecture that can provide\ndynamic compositionality by considering comprehensive syntactic information\nderived from both the structure and linguistic tags. Specifically, we introduce\na structure-aware tag representation constructed by a separate tag-level\ntree-LSTM. With this, we can control the composition function of the existing\nword-level tree-LSTM by augmenting the representation as a supplementary input\nto the gate functions of the tree-LSTM. In extensive experiments, we show that\nmodels built upon the proposed architecture obtain superior or competitive\nperformance on several sentence-level tasks such as sentiment analysis and\nnatural language inference when compared against previous tree-structured\nmodels and other sophisticated neural models.","url_abs":"http://arxiv.org/abs/1809.02286v2","url_pdf":"http://arxiv.org/pdf/1809.02286v2.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":"dynamic-compositionality-in-recursive-neural","repo_url":"https://github.com/galsang/SATA-Tree-LSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dynamic-compositionality-in-recursive-neural","repo_url":"https://github.com/galsang/galsang","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}