{"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/crf-autoencoder-for-unsupervised-dependency","title":"CRF Autoencoder for Unsupervised Dependency Parsing","arxiv_id":"1708.01018","date":"2017-08-03","proceeding":"EMNLP 2017 9","authors":["Jiong Cai","Yong Jiang","Kewei Tu"],"abstract":"Unsupervised dependency parsing, which tries to discover linguistic\ndependency structures from unannotated data, is a very challenging task. Almost\nall previous work on this task focuses on learning generative models. In this\npaper, we develop an unsupervised dependency parsing model based on the CRF\nautoencoder. The encoder part of our model is discriminative and globally\nnormalized which allows us to use rich features as well as universal linguistic\npriors. We propose an exact algorithm for parsing as well as a tractable\nlearning algorithm. We evaluated the performance of our model on eight\nmultilingual treebanks and found that our model achieved comparable performance\nwith state-of-the-art approaches.","url_abs":"http://arxiv.org/abs/1708.01018v1","url_pdf":"http://arxiv.org/pdf/1708.01018v1.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":"crf-autoencoder-for-unsupervised-dependency","repo_url":"https://github.com/caijiong/CRFAE-Dep-Parser","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-grammar-induction","task_name":"Dependency Grammar Induction"},{"task_slug":"unsupervised-dependency-parsing","task_name":"Unsupervised Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.01018","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}