Knowledge Commons of Institute of Automation,CAS
MSMO: Multimodal Summarization with Multimodal Output | |
Zhu, Junnan1,2; Li, Haoran1,2; Liu, Tianshang1,2; Zhou, Yu1,2; Zhang, Jiajun1,2; Zong, Chengqing1,2,3 | |
2018-11 | |
会议名称 | Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing |
会议日期 | 2018.10.31-2018.11.4 |
会议地点 | Brussels, Belgium |
会议录编者/会议主办者 | Association for Computational Linguistics |
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. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39082 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | 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 |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhu, Junnan,Li, Haoran,Liu, Tianshang,et al. MSMO: Multimodal Summarization with Multimodal Output[C]//Association for Computational Linguistics,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 | ||
EMNLP18.pdf(3625KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论