{"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/multitask-parsing-across-semantic","title":"Multitask Parsing Across Semantic Representations","arxiv_id":"1805.00287","date":"2018-05-01","proceeding":"ACL 2018 7","authors":["Daniel Hershcovich","Omri Abend","Ari Rappoport"],"abstract":"The ability to consolidate information of different types is at the core of\nintelligence, and has tremendous practical value in allowing learning for one\ntask to benefit from generalizations learned for others. In this paper we\ntackle the challenging task of improving semantic parsing performance, taking\nUCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD)\nparsing as auxiliary tasks. We experiment on three languages, using a uniform\ntransition-based system and learning architecture for all parsing tasks.\nDespite notable conceptual, formal and domain differences, we show that\nmultitask learning significantly improves UCCA parsing in both in-domain and\nout-of-domain settings.","url_abs":"http://arxiv.org/abs/1805.00287v1","url_pdf":"http://arxiv.org/pdf/1805.00287v1.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":"multitask-parsing-across-semantic","repo_url":"https://github.com/danielhers/tupa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"ucca-parsing","task_name":"UCCA Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/ucca-parsing-on-semeval-2019-task-1","task":"UCCA Parsing","dataset":"SemEval 2019 Task 1","model":"Transition-based + MTL","rank_in_archive_order":3,"of":4,"metrics":{"English-20K (open) F1":"68.4","English-Wiki (open) F1":"73.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.00287","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}