{"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/classifying-relations-via-long-short-term","title":"Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path","arxiv_id":"1508.03720","date":"2015-08-15","proceeding":null,"authors":["Xu Yan","Lili Mou","Ge Li","Yunchuan Chen","Hao Peng","Zhi Jin"],"abstract":"Relation classification is an important research arena in the field of\nnatural language processing (NLP). In this paper, we present SDP-LSTM, a novel\nneural network to classify the relation of two entities in a sentence. Our\nneural architecture leverages the shortest dependency path (SDP) between two\nentities; multichannel recurrent neural networks, with long short term memory\n(LSTM) units, pick up heterogeneous information along the SDP. Our proposed\nmodel has several distinct features: (1) The shortest dependency paths retain\nmost relevant information (to relation classification), while eliminating\nirrelevant words in the sentence. (2) The multichannel LSTM networks allow\neffective information integration from heterogeneous sources over the\ndependency paths. (3) A customized dropout strategy regularizes the neural\nnetwork to alleviate overfitting. We test our model on the SemEval 2010\nrelation classification task, and achieve an $F_1$-score of 83.7\\%, higher than\ncompeting methods in the literature.","url_abs":"http://arxiv.org/abs/1508.03720v1","url_pdf":"http://arxiv.org/pdf/1508.03720v1.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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"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":[{"leaderboard":"/sota/relation-classification-on-semeval-2010-task-1","task":"Relation Classification","dataset":"SemEval 2010 Task 8","model":"SDP-LSTM","rank_in_archive_order":4,"of":6,"metrics":{"F1":"83.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1508.03720","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}