{"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/bidirectional-tree-structured-lstm-with-head","title":"Bidirectional Tree-Structured LSTM with Head Lexicalization","arxiv_id":"1611.06788","date":"2016-11-21","proceeding":null,"authors":["Zhiyang Teng","Yue Zhang"],"abstract":"Sequential LSTM has been extended to model tree structures, giving\ncompetitive results for a number of tasks. Existing methods model constituent\ntrees by bottom-up combinations of constituent nodes, making direct use of\ninput word information only for leaf nodes. This is different from sequential\nLSTMs, which contain reference to input words for each node. In this paper, we\npropose a method for automatic head-lexicalization for tree-structure LSTMs,\npropagating head words from leaf nodes to every constituent node. In addition,\nenabled by head lexicalization, we build a tree LSTM in the top-down direction,\nwhich corresponds to bidirectional sequential LSTM structurally. Experiments\nshow that both extensions give better representations of tree structures. Our\nfinal model gives the best results on the Standford Sentiment Treebank and\nhighly competitive results on the TREC question type classification task.","url_abs":"http://arxiv.org/abs/1611.06788v1","url_pdf":"http://arxiv.org/pdf/1611.06788v1.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":"bidirectional-tree-structured-lstm-with-head","repo_url":"https://github.com/zeeeyang/lexicalized_bitreelstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"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":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}