{"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/riga-at-semeval-2016-task-8-impact-of-smatch","title":"RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy","arxiv_id":"1604.01278","date":"2016-04-05","proceeding":"SEMEVAL 2016 6","authors":["Guntis Barzdins","Didzis Gosko"],"abstract":"Two extensions to the AMR smatch scoring script are presented. The first\nextension com-bines the smatch scoring script with the C6.0 rule-based\nclassifier to produce a human-readable report on the error patterns frequency\nobserved in the scored AMR graphs. This first extension results in 4% gain over\nthe state-of-art CAMR baseline parser by adding to it a manually crafted\nwrapper fixing the identified CAMR parser errors. The second extension combines\na per-sentence smatch with an en-semble method for selecting the best AMR graph\namong the set of AMR graphs for the same sentence. This second modification\nau-tomatically yields further 0.4% gain when ap-plied to outputs of two\nnondeterministic AMR parsers: a CAMR+wrapper parser and a novel character-level\nneural translation AMR parser. For AMR parsing task the character-level neural\ntranslation attains surprising 7% gain over the carefully optimized word-level\nneural translation. Overall, we achieve smatch F1=62% on the SemEval-2016\nofficial scor-ing set and F1=67% on the LDC2015E86 test set.","url_abs":"http://arxiv.org/abs/1604.01278v1","url_pdf":"http://arxiv.org/pdf/1604.01278v1.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":"riga-at-semeval-2016-task-8-impact-of-smatch","repo_url":"https://github.com/didzis/smatchTools","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"riga-at-semeval-2016-task-8-impact-of-smatch","repo_url":"https://github.com/didzis/tensorflowAMR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"amr-parsing","task_name":"AMR Parsing"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1604.01278","atlas_url":"https://app.syntology.ai/?focus=1604.01278","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}