Punctuation Prediction for Chinese Spoken Sentence Based on Model Combination
Chen, Xiao; Ke, Dengfeng; Xu, Bo
2013-11
会议名称International Conference on Intelligent Systems and Knowledge Engineering
会议录名称Proceedings of the Eighth International Conference on Intelligent Systems and Knowledge Engineering
会议日期20-23
会议地点Shenzhen
摘要
Punctuation prediction is very important for automatic speech recognition. It greatly improves readability of transcripts and user experience, and facilitates following natural language processing tasks. In this study, we develop a model combination based approach for the recovery of punctuation for Chinese spoken sentence. Our approach models the relationships between punctuation and sentence by the different ways of sentence representation. And the relationships modeled are combined by multi-layer perception to predict punctuation (period, question mark and exclamation mark). Different from previous studies, our proposed approach is designed to use global lexical information, not only local information. Results indicate that, compared with the baseline, our proposed method results in an absolute improvement of 10.0% un-weighted accuracy and 4.9% weighted accuracy, respectively. Our approach finally achieves an un-weighted accuracy of 86.9% and a weighted accuracy of 92.4%.

关键词Punctuation Prediction Model Combine Global Lexical Information
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11821
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Chen, Xiao
作者单位Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Chen, Xiao,Ke, Dengfeng,Xu, Bo. Punctuation Prediction for Chinese Spoken Sentence Based on Model Combination[C],2013.
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
2013ISKE.pdf(144KB)会议论文 开放获取CC BY-NC-SA浏览 请求全文
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
[Chen, Xiao]的文章
[Ke, Dengfeng]的文章
[Xu, Bo]的文章
百度学术
百度学术中相似的文章
[Chen, Xiao]的文章
[Ke, Dengfeng]的文章
[Xu, Bo]的文章
必应学术
必应学术中相似的文章
[Chen, Xiao]的文章
[Ke, Dengfeng]的文章
[Xu, Bo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2013ISKE.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。