ShanghaiTech University Knowledge Management System
Deep Inside-outside Recursive Autoencoder with All-span Objective | |
2020-12 | |
会议录名称 | THE 28TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL LINGUISTICS (COLING) |
发表状态 | 正式接收 |
DOI | / |
摘要 | Deep inside-outside recursive autoencoder (DIORA) is a neural-based model designed for unsupervised constituency parsing. During its forward computation, it provides phrase and contextual representations for all spans in the input sentence. By utilizing the contextual representation of each leaf-level span, the span of length 1, to reconstruct the word inside the span, the model is trained without labeled data. In this work, we extend the training objective of DIORA by making use of all spans instead of only leaf-level spans. We test our new training objective on datasets of two languages: English and Japanese, and empirically show that our method achieves improvement in parsing accuracy over the original DIORA |
会议名称 | the 28th International Conference on Computational Linguistics (COLING) |
文献类型 | 会议论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/124039 |
专题 | 信息科学与技术学院_硕士生 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_本科生 信息科学与技术学院_博士生 |
通讯作者 | Tu, Kewei |
作者单位 | 1.School of Information Science and Technology, ShanghaiTech University 2.University of Chinese Academy of Sciences 3.Shanghai Engineering Research Center of Intelligent Vision and Imaging 4.Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences |
第一作者单位 | 信息科学与技术学院 |
通讯作者单位 | 信息科学与技术学院 |
第一作者的第一单位 | 信息科学与技术学院 |
推荐引用方式 GB/T 7714 | Hong, Ruyue,Cai, Jiong,Tu, Kewei. Deep Inside-outside Recursive Autoencoder with All-span Objective[C],2020. |
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。