{"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/parsing-universal-dependencies-without","title":"Parsing Universal Dependencies without training","arxiv_id":"1701.03163","date":"2017-01-11","proceeding":"EACL 2017 4","authors":["Héctor Martínez Alonso","Željko Agić","Barbara Plank","Anders Søgaard"],"abstract":"We propose UDP, the first training-free parser for Universal Dependencies\n(UD). Our algorithm is based on PageRank and a small set of head attachment\nrules. It features two-step decoding to guarantee that function words are\nattached as leaf nodes. The parser requires no training, and it is competitive\nwith a delexicalized transfer system. UDP offers a linguistically sound\nunsupervised alternative to cross-lingual parsing for UD, which can be used as\na baseline for such systems. The parser has very few parameters and is\ndistinctly robust to domain change across languages.","url_abs":"http://arxiv.org/abs/1701.03163v1","url_pdf":"http://arxiv.org/pdf/1701.03163v1.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":"parsing-universal-dependencies-without","repo_url":"https://github.com/hectormartinez/ud_unsup_parser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.03163","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}