作者其他论文
文献详情
Lexical story co-segmentation of Chinese broadcast news
文献类型:会议
作者:Feng, Wei[1]  Nie, Xuecheng[2]  Wan, Liang[3]  Xie, Lei[4]  Jiang, Jianmin[5]  
机构:[1]School of Computer Science and Technology, Tianjin University, Tianjin, China
[2]School of Computer Science and Technology, Tianjin University, Tianjin, China
[3]School of Computer Software, Tianjin University, Tianjin, China
[4]School of Computer Science, Northwestern Polytechnical University, Xi'an, China
[5]School of Computer Science and Technology, Tianjin University, Tianjin, China
年:2012
会议名称:13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
页码范围:2283-2286
会议地点:Portland, OR, United states
会议开始日期:2012-09-09
会议结束日期:2012-09-13
收录情况:EI(20132416407772)  
所属部门:计算机学院
人气指数:3727
浏览次数:3692
语言:中文
摘要:
We present an unsupervised technique, namely story cosegmentation, to automatically extract the common stories on the same topic within a pair of Chinese broadcast news transcripts. Unlike classical topic tracking that usually relies on previously trained topic models, our method is purely data-driven and is able to simultaneously determine the common stories of the input texts. Specifically, we propose an iterative four-step MRF solution to the problem of story co-segmentation using lexical cue ...More
0
评论(0 条评论)
登录