{"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/uniparse-a-universal-graph-based-parsing","title":"UniParse: A universal graph-based parsing toolkit","arxiv_id":"1807.04053","date":"2018-07-11","proceeding":"WS (NoDaLiDa) 2019 9","authors":["Daniel Varab","Natalie Schluter"],"abstract":"This paper describes the design and use of the graph-based parsing framework\nand toolkit UniParse, released as an open-source python software package.\nUniParse as a framework novelly streamlines research prototyping, development\nand evaluation of graph-based dependency parsing architectures. UniParse does\nthis by enabling highly efficient, sufficiently independent, easily readable,\nand easily extensible implementations for all dependency parser components. We\ndistribute the toolkit with ready-made configurations as re-implementations of\nall current state-of-the-art first-order graph-based parsers, including even\nmore efficient Cython implementations of both encoders and decoders, as well as\nthe required specialised loss functions.","url_abs":"http://arxiv.org/abs/1807.04053v1","url_pdf":"http://arxiv.org/pdf/1807.04053v1.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":"uniparse-a-universal-graph-based-parsing","repo_url":"https://github.com/ITUnlp/UniParse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}