{"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/unsupervised-dependency-parsing-lets-use","title":"Unsupervised Dependency Parsing: Let's Use Supervised Parsers","arxiv_id":"1504.04666","date":"2015-04-18","proceeding":"HLT 2015 5","authors":["Phong Le","Willem Zuidema"],"abstract":"We present a self-training approach to unsupervised dependency parsing that\nreuses existing supervised and unsupervised parsing algorithms. Our approach,\ncalled `iterated reranking' (IR), starts with dependency trees generated by an\nunsupervised parser, and iteratively improves these trees using the richer\nprobability models used in supervised parsing that are in turn trained on these\ntrees. Our system achieves 1.8% accuracy higher than the state-of-the-part\nparser of Spitkovsky et al. (2013) on the WSJ corpus.","url_abs":"http://arxiv.org/abs/1504.04666v1","url_pdf":"http://arxiv.org/pdf/1504.04666v1.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":[],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"unsupervised-dependency-parsing","task_name":"Unsupervised Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-dependency-parsing-on-penn","task":"Unsupervised Dependency Parsing","dataset":"Penn Treebank","model":"Iterative reranking","rank_in_archive_order":2,"of":6,"metrics":{"UAS":"66.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1504.04666","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}