{"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/cross-lingual-dependency-parsing-with-late","title":"Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages","arxiv_id":"1701.01623","date":"2017-01-06","proceeding":null,"authors":["Michael Sejr Schlichtkrull","Anders Søgaard"],"abstract":"In cross-lingual dependency annotation projection, information is often lost\nduring transfer because of early decoding. We present an end-to-end graph-based\nneural network dependency parser that can be trained to reproduce matrices of\nedge scores, which can be directly projected across word alignments. We show\nthat our approach to cross-lingual dependency parsing is not only simpler, but\nalso achieves an absolute improvement of 2.25% averaged across 10 languages\ncompared to the previous state of the art.","url_abs":"http://arxiv.org/abs/1701.01623v1","url_pdf":"http://arxiv.org/pdf/1701.01623v1.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":"cross-lingual-dependency-parsing-with-late","repo_url":"https://github.com/MichSchli/Tensor-LSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1701.01623","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}