{"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/structured-training-for-neural-network","title":"Structured Training for Neural Network Transition-Based Parsing","arxiv_id":"1506.06158","date":"2015-06-19","proceeding":"IJCNLP 2015 7","authors":["David Weiss","Chris Alberti","Michael Collins","Slav Petrov"],"abstract":"We present structured perceptron training for neural network transition-based\ndependency parsing. We learn the neural network representation using a gold\ncorpus augmented by a large number of automatically parsed sentences. Given\nthis fixed network representation, we learn a final layer using the structured\nperceptron with beam-search decoding. On the Penn Treebank, our parser reaches\n94.26% unlabeled and 92.41% labeled attachment accuracy, which to our knowledge\nis the best accuracy on Stanford Dependencies to date. We also provide in-depth\nablative analysis to determine which aspects of our model provide the largest\ngains in accuracy.","url_abs":"http://arxiv.org/abs/1506.06158v1","url_pdf":"http://arxiv.org/pdf/1506.06158v1.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":"transition-based-dependency-parsing","task_name":"Transition-Based Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dependency-parsing-on-penn-treebank","task":"Dependency Parsing","dataset":"Penn Treebank","model":"Weiss et al.","rank_in_archive_order":19,"of":22,"metrics":{"LAS":"92.06","POS":"97.3","UAS":"94.01"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.06158","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}