CASIA OpenIR  > 复杂系统认知与决策实验室
Bidirectional Sentence Ordering with Interactive Decoding
Guirong Bai1,2; Shizhu HE1,2; Kang Liu1,2; Jun Zhao1,2
发表期刊ACM Transactions on Asian and Low-Resource Language Information Processing
2023-05-30
卷号22期号:2页码:1-15
摘要

Sentence ordering aims at restoring orders of shuffled sentences in a paragraph. Previous methods usually predict orders in a single direction, i.e., from head to tail. However, unidirectional prediction inevitably causes error accumulation, which restricts performance. In this article, we propose a bidirectional ordering method, which predicts orders in both head-to-tail and tail-to-head directions at the same time. In our bidirectional ordering method, two directions can interact with each other and help alleviate the error accumulation problem of ordering. Experiments demonstrate that our method can effectively improve performance of previous models.

语种英语
七大方向——子方向分类自然语言处理
国重实验室规划方向分类语音语言处理
是否有论文关联数据集需要存交
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/57452
专题复杂系统认知与决策实验室
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
第一作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Guirong Bai,Shizhu HE,Kang Liu,et al. Bidirectional Sentence Ordering with Interactive Decoding[J]. ACM Transactions on Asian and Low-Resource Language Information Processing,2023,22(2):1-15.
APA Guirong Bai,Shizhu HE,Kang Liu,&Jun Zhao.(2023).Bidirectional Sentence Ordering with Interactive Decoding.ACM Transactions on Asian and Low-Resource Language Information Processing,22(2),1-15.
MLA Guirong Bai,et al."Bidirectional Sentence Ordering with Interactive Decoding".ACM Transactions on Asian and Low-Resource Language Information Processing 22.2(2023):1-15.
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
3561510.pdf(1080KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Guirong Bai]的文章
[Shizhu HE]的文章
[Kang Liu]的文章
百度学术
百度学术中相似的文章
[Guirong Bai]的文章
[Shizhu HE]的文章
[Kang Liu]的文章
必应学术
必应学术中相似的文章
[Guirong Bai]的文章
[Shizhu HE]的文章
[Kang Liu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 3561510.pdf
格式: Adobe PDF
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。