Self-Attention Based Network for Punctuation Restoration
Feng Wang; Wei Chen; Zhen Yang; Bo Xu
2018
会议名称International Conference on Pattern Recognition
会议日期August 20th-24th 2018
会议地点In Beijing, China
摘要
Inserting proper punctuation into Automatic Speech
Recognizer(ASR) transcription is a challenging and promising
task in real-time Spoken Language Translation(SLT). Traditional
methods built on the sequence labelling framework are weak
in handling the joint punctuation. To tackle this problem, we
propose a novel self-attention based network, which can solve the
aforementioned problem very well. In this work, a light-weight
neural net is proposed to extract the hidden features based solely
on self-attention without any Recurrent Neural Nets(RNN) and
Convolutional Neural Nets(CNN). We conduct extensive experiments
on complex punctuation tasks. The experimental results
show that the proposed model achieves significant improvements
on joint punctuation task while being superior to traditional
methods on simple punctuation task as well.
关键词Punctuation Restoration Self-attention
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/22101
专题数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者Wei Chen
作者单位Institute of Automation Chinese Academy of Science
推荐引用方式
GB/T 7714
Feng Wang,Wei Chen,Zhen Yang,et al. Self-Attention Based Network for Punctuation Restoration[C],2018.
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
Self-Attention Based(282KB)会议论文 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
[Feng Wang]的文章
[Wei Chen]的文章
[Zhen Yang]的文章
百度学术
百度学术中相似的文章
[Feng Wang]的文章
[Wei Chen]的文章
[Zhen Yang]的文章
必应学术
必应学术中相似的文章
[Feng Wang]的文章
[Wei Chen]的文章
[Zhen Yang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Self-Attention Based Network for Punctuation Restoration.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。