{"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/hyperlex-a-large-scale-evaluation-of-graded","title":"HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment","arxiv_id":"1608.02117","date":"2016-08-06","proceeding":"CL 2017 12","authors":["Ivan Vulić","Daniela Gerz","Douwe Kiela","Felix Hill","Anna Korhonen"],"abstract":"We introduce HyperLex - a dataset and evaluation resource that quantifies the\nextent of of the semantic category membership, that is, type-of relation also\nknown as hyponymy-hypernymy or lexical entailment (LE) relation between 2,616\nconcept pairs. Cognitive psychology research has established that typicality\nand category/class membership are computed in human semantic memory as a\ngradual rather than binary relation. Nevertheless, most NLP research, and\nexisting large-scale invetories of concept category membership (WordNet,\nDBPedia, etc.) treat category membership and LE as binary. To address this, we\nasked hundreds of native English speakers to indicate typicality and strength\nof category membership between a diverse range of concept pairs on a\ncrowdsourcing platform. Our results confirm that category membership and LE are\nindeed more gradual than binary. We then compare these human judgements with\nthe predictions of automatic systems, which reveals a huge gap between human\nperformance and state-of-the-art LE, distributional and representation learning\nmodels, and substantial differences between the models themselves. We discuss a\npathway for improving semantic models to overcome this discrepancy, and\nindicate future application areas for improved graded LE systems.","url_abs":"http://arxiv.org/abs/1608.02117v2","url_pdf":"http://arxiv.org/pdf/1608.02117v2.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":"lexical-entailment","task_name":"Lexical Entailment"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[{"slug":"hyperlex","name":"HyperLex","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1608.02117","atlas_url":"https://app.syntology.ai/?focus=1608.02117","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}