MSMO: Multimodal Summarization with Multimodal Output
文献类型:会议论文
作者 | Zhu JN(朱军楠)1,2; Li HR(李浩然)1,2; Liu TS(刘天赏)1,2; Zhou Y(周玉)1,2; Zhang JJ(张家俊)1,2; Zong CQ(宗成庆)1,2,3; Zhou, Yu; Zong, Chengqing; Zhang, Jiajun; Liu, Tianshang |
出版日期 | 2018-11 |
会议日期 | 2018.10.31-2018.11.4 |
会议地点 | Brussels, Belgium |
英文摘要 | Multimodal summarization has drawn much attention due to the rapid growth of multimedia data. The output of the current multimodal summarization systems is usually represented in texts. However, we have found through experiments that multimodal output can significantly improve user satisfaction for informativeness of summaries. In this paper, we propose a novel task, multimodal summarization with multimodal output (MSMO). To handle this task, we first collect a large-scale dataset for MSMO research. We then propose a multimodal attention model to jointly generate text and select the most relevant image from the multimodal input. Finally, to evaluate multimodal outputs, we construct a novel multimodal automatic evaluation (MMAE) method which considers both intramodality salience and intermodality relevance. The experimental results show the effectiveness of MMAE. |
源文献作者 | Association for Computational Linguistics |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/39082] |
专题 | 模式识别国家重点实验室_自然语言处理 |
通讯作者 | Zong CQ(宗成庆); Zong, Chengqing |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, CAS 2.University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
推荐引用方式 GB/T 7714 | Zhu JN,Li HR,Liu TS,et al. MSMO: Multimodal Summarization with Multimodal Output[C]. 见:. Brussels, Belgium. 2018.10.31-2018.11.4. |
入库方式: OAI收割
来源:自动化研究所
其他版本
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。