{"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/learning-semantic-correspondences-with-less","title":"Learning Semantic Correspondences with Less Supervision","arxiv_id":null,"date":"2009-08-01","proceeding":null,"authors":["Percy Liang","Michael Jordan","Dan Klein"],"abstract":"A central problem in grounded language acquisition is learning the correspondences between a\r\nrich world state and a stream of text which references that world state. To deal with the high degree of ambiguity present in this setting, we present\r\na generative model that simultaneously segments\r\nthe text into utterances and maps each utterance\r\nto a meaning representation grounded in the world\r\nstate. We show that our model generalizes across\r\nthree domains of increasing difficulty—Robocup\r\nsportscasting, weather forecasts (a new domain),\r\nand NFL recaps.","url_abs":"https://aclanthology.org/P09-1011","url_pdf":"https://aclanthology.org/P09-1011.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":"learning-semantic-correspondences-with-less","repo_url":"https://worksheets.codalab.org/worksheets/0xd8ae7710960549868c4665d197ecc583","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-acquisition","task_name":"Language Acquisition"}],"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}