{"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/sjtu-nlp-at-semeval-2018-task-9-neural","title":"SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings","arxiv_id":"1805.10465","date":"2018-05-26","proceeding":"SEMEVAL 2018 6","authors":["Zhuosheng Zhang","Jiangtong Li","Hai Zhao","Bingjie Tang"],"abstract":"This paper describes a hypernym discovery system for our participation in the\nSemEval-2018 Task 9, which aims to discover the best (set of) candidate\nhypernyms for input concepts or entities, given the search space of a\npre-defined vocabulary. We introduce a neural network architecture for the\nconcerned task and empirically study various neural network models to build the\nrepresentations in latent space for words and phrases. The evaluated models\ninclude convolutional neural network, long-short term memory network, gated\nrecurrent unit and recurrent convolutional neural network. We also explore\ndifferent embedding methods, including word embedding and sense embedding for\nbetter performance.","url_abs":"http://arxiv.org/abs/1805.10465v1","url_pdf":"http://arxiv.org/pdf/1805.10465v1.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":"hypernym-discovery","task_name":"Hypernym Discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hypernym-discovery-on-general","task":"Hypernym Discovery","dataset":"General","model":"SJTU BCMI","rank_in_archive_order":6,"of":8,"metrics":{"MAP":"5.77","MRR":"10.56","P@5":"5.96"},"uses_additional_data":false},{"leaderboard":"/sota/hypernym-discovery-on-medical-domain","task":"Hypernym Discovery","dataset":"Medical domain","model":"SJTU BCMI","rank_in_archive_order":6,"of":8,"metrics":{"MAP":"11.69","MRR":"25.95","P@5":"11.69"},"uses_additional_data":false},{"leaderboard":"/sota/hypernym-discovery-on-music-domain","task":"Hypernym Discovery","dataset":"Music domain","model":"SJTU BCMI","rank_in_archive_order":5,"of":7,"metrics":{"MAP":"4.71","MRR":"9.15","P@5":"4.91"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}