{"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/depth-bounding-is-effective-improvements-and","title":"Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction","arxiv_id":"1809.03112","date":"2018-09-10","proceeding":"EMNLP 2018 10","authors":["Lifeng Jin","Finale Doshi-Velez","Timothy Miller","William Schuler","Lane Schwartz"],"abstract":"There have been several recent attempts to improve the accuracy of grammar\ninduction systems by bounding the recursive complexity of the induction model\n(Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016; Jin et al.,\n2018). Modern depth-bounded grammar inducers have been shown to be more\naccurate than early unbounded PCFG inducers, but this technique has never been\ncompared against unbounded induction within the same system, in part because\nmost previous depth-bounding models are built around sequence models, the\ncomplexity of which grows exponentially with the maximum allowed depth. The\npresent work instead applies depth bounds within a chart-based Bayesian PCFG\ninducer (Johnson et al., 2007b), where bounding can be switched on and off, and\nthen samples trees with and without bounding. Results show that depth-bounding\nis indeed significantly effective in limiting the search space of the inducer\nand thereby increasing the accuracy of the resulting parsing model. Moreover,\nparsing results on English, Chinese and German show that this bounded model\nwith a new inference technique is able to produce parse trees more accurately\nthan or competitively with state-of-the-art constituency-based grammar\ninduction models.","url_abs":"http://arxiv.org/abs/1809.03112v1","url_pdf":"http://arxiv.org/pdf/1809.03112v1.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":"depth-bounding-is-effective-improvements-and","repo_url":"https://github.com/lifengjin/dimi_emnlp18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.03112","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}