{"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/unlexicalized-transition-based-discontinuous","title":"Unlexicalized Transition-based Discontinuous Constituency Parsing","arxiv_id":"1902.08912","date":"2019-02-24","proceeding":"TACL 2019 3","authors":["Maximin Coavoux","Benoît Crabbé","Shay B. Cohen"],"abstract":"Lexicalized parsing models are based on the assumptions that (i) constituents\nare organized around a lexical head (ii) bilexical statistics are crucial to\nsolve ambiguities. In this paper, we introduce an unlexicalized\ntransition-based parser for discontinuous constituency structures, based on a\nstructure-label transition system and a bi-LSTM scoring system. We compare it\nto lexicalized parsing models in order to address the question of\nlexicalization in the context of discontinuous constituency parsing. Our\nexperiments show that unlexicalized models systematically achieve higher\nresults than lexicalized models, and provide additional empirical evidence that\nlexicalization is not necessary to achieve strong parsing results. Our best\nunlexicalized model sets a new state of the art on English and German\ndiscontinuous constituency treebanks. We further provide a per-phenomenon\nanalysis of its errors on discontinuous constituents.","url_abs":"http://arxiv.org/abs/1902.08912v1","url_pdf":"http://arxiv.org/pdf/1902.08912v1.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":"unlexicalized-transition-based-discontinuous","repo_url":"https://github.com/mcoavoux/mtg_TACL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.08912","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}