{"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/universal-dependency-parsing-from-scratch","title":"Universal Dependency Parsing from Scratch","arxiv_id":"1901.10457","date":"2019-01-29","proceeding":"CONLL 2018 10","authors":["Peng Qi","Timothy Dozat","Yuhao Zhang","Christopher D. Manning"],"abstract":"This paper describes Stanford's system at the CoNLL 2018 UD Shared Task. We\nintroduce a complete neural pipeline system that takes raw text as input, and\nperforms all tasks required by the shared task, ranging from tokenization and\nsentence segmentation, to POS tagging and dependency parsing. Our single system\nsubmission achieved very competitive performance on big treebanks. Moreover,\nafter fixing an unfortunate bug, our corrected system would have placed the\n2nd, 1st, and 3rd on the official evaluation metrics LAS,MLAS, and BLEX, and\nwould have outperformed all submission systems on low-resource treebank\ncategories on all metrics by a large margin. We further show the effectiveness\nof different model components through extensive ablation studies.","url_abs":"http://arxiv.org/abs/1901.10457v1","url_pdf":"http://arxiv.org/pdf/1901.10457v1.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":"universal-dependency-parsing-from-scratch","repo_url":"https://github.com/stanfordnlp/stanfordnlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"pos-tagging","task_name":"POS Tagging"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-segmentation","task_name":"Sentence segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dependency-parsing-on-universal-dependencies","task":"Dependency Parsing","dataset":"Universal Dependencies","model":"Stanford+","rank_in_archive_order":4,"of":6,"metrics":{"BLEX":"65.28","LAS":"74.16","UAS":"62.08"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.10457","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}