ShanghaiTech University Knowledge Management System
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols | |
2021-04-28 | |
状态 | 已发表 |
摘要 | Probabilistic context-free grammars (PCFGs) with neural parameterization have been shown to be effective in unsupervised phrase-structure grammar induction. However, due to the cubic computational complexity of PCFG representation and parsing, previous approaches cannot scale up to a relatively large number of (nonterminal and preterminal) symbols. In this work, we present a new parameterization form of PCFGs based on tensor decomposition, which has at most quadratic computational complexity in the symbol number and therefore allows us to use a much larger number of symbols. We further use neural parameterization for the new form to improve unsupervised parsing performance. We evaluate our model across ten languages and empirically demonstrate the effectiveness of using more symbols. |
DOI | arXiv:2104.13727 |
相关网址 | 查看原文 |
出处 | Arxiv |
WOS记录号 | PPRN:11721387 |
WOS类目 | Computer Science, Interdisciplinary Applications |
资助项目 | National Natural Science Foundation of China[61976139] |
文献类型 | 预印本 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/348570 |
专题 | 信息科学与技术学院 信息科学与技术学院_PI研究组_屠可伟组 信息科学与技术学院_硕士生 |
作者单位 | 1.Shanghai Tech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 2.Univ Chinese Acad Sci, Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Shanghai Engn Res Ctr Intelligent Vis & Imaging, Shanghai, Peoples R China 3.Univ Edinburgh, ILCC, Edinburgh, Scotland |
推荐引用方式 GB/T 7714 | Yang, Songlin,Zhao, Yanpeng,Tu, Kewei. PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols. 2021. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。