{"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/robust-incremental-neural-semantic-graph","title":"Robust Incremental Neural Semantic Graph Parsing","arxiv_id":"1704.07092","date":"2017-04-24","proceeding":"ACL 2017 7","authors":["Jan Buys","Phil Blunsom"],"abstract":"Parsing sentences to linguistically-expressive semantic representations is a\nkey goal of Natural Language Processing. Yet statistical parsing has focused\nalmost exclusively on bilexical dependencies or domain-specific logical forms.\nWe propose a neural encoder-decoder transition-based parser which is the first\nfull-coverage semantic graph parser for Minimal Recursion Semantics (MRS). The\nmodel architecture uses stack-based embedding features, predicting graphs\njointly with unlexicalized predicates and their token alignments. Our parser is\nmore accurate than attention-based baselines on MRS, and on an additional\nAbstract Meaning Representation (AMR) benchmark, and GPU batch processing makes\nit an order of magnitude faster than a high-precision grammar-based parser.\nFurther, the 86.69% Smatch score of our MRS parser is higher than the\nupper-bound on AMR parsing, making MRS an attractive choice as a semantic\nrepresentation.","url_abs":"http://arxiv.org/abs/1704.07092v2","url_pdf":"http://arxiv.org/pdf/1704.07092v2.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":"robust-incremental-neural-semantic-graph","repo_url":"https://github.com/janmbuys/DeepDeepParser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"amr-parsing","task_name":"AMR Parsing"},{"task_slug":"abstract-meaning-representation","task_name":"Abstract Meaning Representation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.07092","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}