{"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/unanimous-prediction-for-100-precision-with","title":"Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings","arxiv_id":"1606.06368","date":"2016-06-20","proceeding":null,"authors":["Fereshte Khani","Martin Rinard","Percy Liang"],"abstract":"Can we train a system that, on any new input, either says \"don't know\" or\nmakes a prediction that is guaranteed to be correct? We answer the question in\nthe affirmative provided our model family is well-specified. Specifically, we\nintroduce the unanimity principle: only predict when all models consistent with\nthe training data predict the same output. We operationalize this principle for\nsemantic parsing, the task of mapping utterances to logical forms. We develop a\nsimple, efficient method that reasons over the infinite set of all consistent\nmodels by only checking two of the models. We prove that our method obtains\n100% precision even with a modest amount of training data from a possibly\nadversarial distribution. Empirically, we demonstrate the effectiveness of our\napproach on the standard GeoQuery dataset.","url_abs":"http://arxiv.org/abs/1606.06368v2","url_pdf":"http://arxiv.org/pdf/1606.06368v2.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":"unanimous-prediction-for-100-precision-with","repo_url":"https://worksheets.codalab.org/worksheets/0x593676a278fc4e5abe2d8bac1e3df486","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1606.06368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}