{"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/grammar-induction-with-neural-language-models","title":"Grammar Induction with Neural Language Models: An Unusual Replication","arxiv_id":"1808.10000","date":"2018-08-29","proceeding":"EMNLP (ACL) 2018 10","authors":["Phu Mon Htut","Kyunghyun Cho","Samuel R. Bowman"],"abstract":"A substantial thread of recent work on latent tree learning has attempted to\ndevelop neural network models with parse-valued latent variables and train them\non non-parsing tasks, in the hope of having them discover interpretable tree\nstructure. In a recent paper, Shen et al. (2018) introduce such a model and\nreport near-state-of-the-art results on the target task of language modeling,\nand the first strong latent tree learning result on constituency parsing. In an\nattempt to reproduce these results, we discover issues that make the original\nresults hard to trust, including tuning and even training on what is\neffectively the test set. Here, we attempt to reproduce these results in a fair\nexperiment and to extend them to two new datasets. We find that the results of\nthis work are robust: All variants of the model under study outperform all\nlatent tree learning baselines, and perform competitively with symbolic grammar\ninduction systems. We find that this model represents the first empirical\nsuccess for latent tree learning, and that neural network language modeling\nwarrants further study as a setting for grammar induction.","url_abs":"http://arxiv.org/abs/1808.10000v1","url_pdf":"http://arxiv.org/pdf/1808.10000v1.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":"grammar-induction-with-neural-language-models","repo_url":"https://github.com/nyu-mll/PRPN-Analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.10000","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}