{"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/reified-context-models","title":"Reified Context Models","arxiv_id":"1502.06665","date":"2015-02-24","proceeding":null,"authors":["Jacob Steinhardt","Percy Liang"],"abstract":"A classic tension exists between exact inference in a simple model and\napproximate inference in a complex model. The latter offers expressivity and\nthus accuracy, but the former provides coverage of the space, an important\nproperty for confidence estimation and learning with indirect supervision. In\nthis work, we introduce a new approach, reified context models, to reconcile\nthis tension. Specifically, we let the amount of context (the arity of the\nfactors in a graphical model) be chosen \"at run-time\" by reifying it---that is,\nletting this choice itself be a random variable inside the model. Empirically,\nwe show that our approach obtains expressivity and coverage on three natural\nlanguage tasks.","url_abs":"http://arxiv.org/abs/1502.06665v1","url_pdf":"http://arxiv.org/pdf/1502.06665v1.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":"reified-context-models","repo_url":"https://worksheets.codalab.org/worksheets/0x8967960a7c644492974871ee60198401","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}