SPE-71.6
END-TO-END SPEECH SUMMARIZATION USING RESTRICTED SELF-ATTENTION
Roshan Sharma, Shruti Palaskar, Alan W Black, Florian Metze, Carnegie Mellon University, United States of America
Session:
Text Completion and Summarization
Track:
Speech and Language Processing
Location:
Gather Area E
Presentation Time:
Thu, 12 May, 21:00 - 21:45 China Time (UTC +8)
Thu, 12 May, 13:00 - 13:45 UTC
Thu, 12 May, 13:00 - 13:45 UTC
Session Chair:
Florian Metze, Carnegie Mellon University
Session SPE-71
SPE-71.1: SELF-ATTENTION FOR INCOMPLETE UTTERANCE REWRITING
Yong Zhang, Zhitao Li, Jianzong Wang, Ning Cheng, Jing Xiao, Ping An Technology (Shenzhen) Co., Ltd., China
SPE-71.2: MULTI-TURN INCOMPLETE UTTERANCE RESTORATION AS OBJECT DETECTION
Wangjie Jiang, Siheng Li, Jiayi Li, Yujiu Yang, Tsinghua University, China
SPE-71.3: CLSEG: Contrastive Learning of Story Ending Generation
Yuqiang Xie, Yue Hu, Luxi Xing, Yunpeng Li, Wei Peng, Ping Guo, Institute of Information Engineering, Chinese Academy of Sciences, China
SPE-71.4: Explicitly Modeling Importance and Coherence for Timeline Summarization
Qianren Mao, Jianxin Li, Jiazheng Wang, Xi Li, Peng Hao, Beihang University (BUAA), China; Lihong Wang, CNCERT/CC, China; Zheng Wang, University of Leeds, United Kingdom of Great Britain and Northern Ireland
SPE-71.5: TED TALK TEASER GENERATION WITH PRE-TRAINED MODELS
Gianluca Vico, Jan Niehues, Maastricht University, Netherlands
SPE-71.6: END-TO-END SPEECH SUMMARIZATION USING RESTRICTED SELF-ATTENTION
Roshan Sharma, Shruti Palaskar, Alan W Black, Florian Metze, Carnegie Mellon University, United States of America