ShanghaiTech University Knowledge Management System
Semi-supervised structured prediction with neural CRF autoencoder | |
2017 | |
会议录名称 | 2017 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2017 |
页码 | 1701-1711 |
发表状态 | 已发表 |
摘要 | In this paper we propose an end-to-end neural CRF autoencoder (NCRF-AE) model for semi-supervised learning of sequential structured prediction problems. Our NCRF-AE consists of two parts: an encoder which is a CRF model enhanced by deep neural networks, and a decoder which is a generative model trying to reconstruct the input. Our model has a unified structure with different loss functions for labeled and unlabeled data with shared parameters. We developed a variation of the EM algorithm for optimizing both the encoder and the decoder simultaneously by decoupling their parameters. Our experimental results over the Part-of-Speech (POS) tagging task on eight different languages, show that the NCRF-AE model can outperform competitive systems in both supervised and semi-supervised scenarios. © 2017 Association for Computational Linguistics. |
会议地点 | Copenhagen, Denmark |
收录类别 | EI |
出版者 | Association for Computational Linguistics (ACL) |
EI入藏号 | 20194207538747 |
EI主题词 | Decoding ; Deep neural networks ; Learning algorithms ; Machine learning ; Signal encoding ; Supervised learning |
EI分类号 | Information Theory and Signal Processing:716.1 ; Data Processing and Image Processing:723.2 |
原始文献类型 | Conference article (CA) |
文献类型 | 会议论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29393 |
专题 | 信息科学与技术学院_博士生 信息科学与技术学院_PI研究组_屠可伟组 |
作者单位 | 1.Department of Computer Science, Purdue University, West Lafayette, United States 2.School of Information Science and Technology, ShanghaiTech University, Shanghai, China |
推荐引用方式 GB/T 7714 | Zhang, Xiao,Jiang, Yong,Peng, Hao,et al. Semi-supervised structured prediction with neural CRF autoencoder[C]:Association for Computational Linguistics (ACL),2017:1701-1711. |
条目包含的文件 | 下载所有文件 | |||||
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。