{"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/instantiation","title":"Instantiation","arxiv_id":"1808.01662","date":"2018-08-05","proceeding":null,"authors":["Abhijeet Gupta","Gemma Boleda","Sebastian Pado"],"abstract":"In computational linguistics, a large body of work exists on distributed\nmodeling of lexical relations, focussing largely on lexical relations such as\nhypernymy (scientist -- person) that hold between two categories, as expressed\nby common nouns. In contrast, computational linguistics has paid little\nattention to entities denoted by proper nouns (Marie Curie, Mumbai, ...). These\nhave investigated in detail by the Knowledge Representation and Semantic Web\ncommunities, but generally not with regard to their linguistic properties.\n  Our paper closes this gap by investigating and modeling the lexical relation\nof instantiation, which holds between an entity-denoting and a\ncategory-denoting expression (Marie Curie -- scientist or Mumbai -- city). We\npresent a new, principled dataset for the task of instantiation detection as\nwell as experiments and analyses on this dataset. We obtain the following\nresults: (a), entities belonging to one category form a region in\ndistributional space, but the embedding for the category word is typically\nlocated outside this subspace; (b) it is easy to learn to distinguish entities\nfrom categories from distributional evidence, but due to (a), instantiation\nproper is much harder to learn when using common nouns as representations of\ncategories; (c) this problem can be alleviated by using category\nrepresentations based on entity rather than category word embeddings.","url_abs":"http://arxiv.org/abs/1808.01662v1","url_pdf":"http://arxiv.org/pdf/1808.01662v1.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":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[{"slug":"instantiation","name":"Instantiation Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}