{"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/enteval-a-holistic-evaluation-benchmark-for","title":"EntEval: A Holistic Evaluation Benchmark for Entity Representations","arxiv_id":"1909.00137","date":"2019-08-31","proceeding":"IJCNLP 2019 11","authors":["Mingda Chen","Zewei Chu","Yang Chen","Karl Stratos","Kevin Gimpel"],"abstract":"Rich entity representations are useful for a wide class of problems involving entities. Despite their importance, there is no standardized benchmark that evaluates the overall quality of entity representations. In this work, we propose EntEval: a test suite of diverse tasks that require nontrivial understanding of entities including entity typing, entity similarity, entity relation prediction, and entity disambiguation. In addition, we develop training techniques for learning better entity representations by using natural hyperlink annotations in Wikipedia. We identify effective objectives for incorporating the contextual information in hyperlinks into state-of-the-art pretrained language models and show that they improve strong baselines on multiple EntEval tasks.","url_abs":"https://arxiv.org/abs/1909.00137v2","url_pdf":"https://arxiv.org/pdf/1909.00137v2.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":"enteval-a-holistic-evaluation-benchmark-for","repo_url":"https://github.com/ZeweiChu/EntEval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"enteval-a-holistic-evaluation-benchmark-for","repo_url":"https://github.com/mingdachen/bilm-tf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"entity-disambiguation","task_name":"Entity Disambiguation"},{"task_slug":"entity-typing","task_name":"Entity Typing"},{"task_slug":"relation-prediction","task_name":"Relation Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.00137","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}