{"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/in-search-of-an-entity-resolution-oasis","title":"In Search of an Entity Resolution OASIS: Optimal Asymptotic Sequential Importance Sampling","arxiv_id":"1703.00617","date":"2017-03-02","proceeding":null,"authors":["Neil G. Marchant","Benjamin I. P. Rubinstein"],"abstract":"Entity resolution (ER) presents unique challenges for evaluation methodology.\nWhile crowdsourcing platforms acquire ground truth, sound approaches to\nsampling must drive labelling efforts. In ER, extreme class imbalance between\nmatching and non-matching records can lead to enormous labelling requirements\nwhen seeking statistically consistent estimates for rigorous evaluation. This\npaper addresses this important challenge with the OASIS algorithm: a sampler\nand F-measure estimator for ER evaluation. OASIS draws samples from a (biased)\ninstrumental distribution, chosen to ensure estimators with optimal asymptotic\nvariance. As new labels are collected OASIS updates this instrumental\ndistribution via a Bayesian latent variable model of the annotator oracle, to\nquickly focus on unlabelled items providing more information. We prove that\nresulting estimates of F-measure, precision, recall converge to the true\npopulation values. Thorough comparisons of sampling methods on a variety of ER\ndatasets demonstrate significant labelling reductions of up to 83% without loss\nto estimate accuracy.","url_abs":"http://arxiv.org/abs/1703.00617v3","url_pdf":"http://arxiv.org/pdf/1703.00617v3.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":"in-search-of-an-entity-resolution-oasis","repo_url":"https://github.com/ngmarchant/oasis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"entity-resolution","task_name":"Entity Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}