Second-Order Unsupervised Neural Dependency Parsing
2020-12
会议录名称THE 28TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL LINGUISTICS (COLING)
发表状态已发表
DOIhttps://doi.org/10.48550/arXiv.2010.14720
摘要

Most of the unsupervised dependency parsers are based on first-order probabilistic generative models that only consider local parent-child information. Inspired by second-order supervised dependency parsing, we proposed a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information. We also propose novel design of the neural parameterization and optimization methods of the dependency models. In secondorder models, the number of grammar rules grows cubically with the increase of vocabulary size, making it difficult to train lexicalized models that may contain thousands of words. To circumvent this problem while still benefiting from both second-order parsing and lexicalization, we use the agreement-based learning framework to jointly train a second-order unlexicalized model and a first-order lexicalized model. Experiments on multiple datasets show the effectiveness of our second-order models compared with recent state-of-the-art methods. Our joint model achieves a 10% improvement over the previous state-of-the-art parser on the full WSJ test set.

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/124037
专题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
通讯作者Tu, Kewei
作者单位
1.School of Information Science and Technology, Shanghaitech University
2.Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences
3.University of Chinese Academy of Sciences
4.Alibaba DAMO Academy, Alibaba Group
5.Department of Computer Science, National University of Singapore
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
Yang, Songlin,Jiang, Yong,Han, Wenjuan,et al. Second-Order Unsupervised Neural Dependency Parsing[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
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Yang, Songlin]的文章
[Jiang, Yong]的文章
[Han, Wenjuan]的文章
百度学术
百度学术中相似的文章
[Yang, Songlin]的文章
[Jiang, Yong]的文章
[Han, Wenjuan]的文章
必应学术
必应学术中相似的文章
[Yang, Songlin]的文章
[Jiang, Yong]的文章
[Han, Wenjuan]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。