{"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/training-with-exploration-improves-a-greedy","title":"Training with Exploration Improves a Greedy Stack-LSTM Parser","arxiv_id":"1603.03793","date":"2016-03-11","proceeding":null,"authors":["Miguel Ballesteros","Yoav Goldberg","Chris Dyer","Noah A. Smith"],"abstract":"We adapt the greedy Stack-LSTM dependency parser of Dyer et al. (2015) to\nsupport a training-with-exploration procedure using dynamic oracles(Goldberg\nand Nivre, 2013) instead of cross-entropy minimization. This form of training,\nwhich accounts for model predictions at training time rather than assuming an\nerror-free action history, improves parsing accuracies for both English and\nChinese, obtaining very strong results for both languages. We discuss some\nmodifications needed in order to get training with exploration to work well for\na probabilistic neural-network.","url_abs":"http://arxiv.org/abs/1603.03793v2","url_pdf":"http://arxiv.org/pdf/1603.03793v2.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":null,"task_name":"Chinese Dependency Parsing"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dependency-parsing-on-penn-treebank","task":"Dependency Parsing","dataset":"Penn Treebank","model":"Arc-hybrid","rank_in_archive_order":21,"of":22,"metrics":{"LAS":"91.42","POS":"97.3","UAS":"93.56"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.03793","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}