{"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/gaussian-mixture-latent-vector-grammars","title":"Gaussian Mixture Latent Vector Grammars","arxiv_id":"1805.04688","date":"2018-05-12","proceeding":"ACL 2018 7","authors":["Yanpeng Zhao","Liwen Zhang","Kewei Tu"],"abstract":"We introduce Latent Vector Grammars (LVeGs), a new framework that extends\nlatent variable grammars such that each nonterminal symbol is associated with a\ncontinuous vector space representing the set of (infinitely many) subtypes of\nthe nonterminal. We show that previous models such as latent variable grammars\nand compositional vector grammars can be interpreted as special cases of LVeGs.\nWe then present Gaussian Mixture LVeGs (GM-LVeGs), a new special case of LVeGs\nthat uses Gaussian mixtures to formulate the weights of production rules over\nsubtypes of nonterminals. A major advantage of using Gaussian mixtures is that\nthe partition function and the expectations of subtype rules can be computed\nusing an extension of the inside-outside algorithm, which enables efficient\ninference and learning. We apply GM-LVeGs to part-of-speech tagging and\nconstituency parsing and show that GM-LVeGs can achieve competitive accuracies.\nOur code is available at https://github.com/zhaoyanpeng/lveg.","url_abs":"http://arxiv.org/abs/1805.04688v1","url_pdf":"http://arxiv.org/pdf/1805.04688v1.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":"gaussian-mixture-latent-vector-grammars","repo_url":"https://github.com/zhaoyanpeng/lveg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"},{"task_slug":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.04688","atlas_url":"https://app.syntology.ai/?focus=1805.04688","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}