CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
MSMO: Multimodal Summarization with Multimodal Output
Zhu, Junnan; Li, Haoran; Liu, Tianshang; Zhou, Yu; Zhang, Jiajun; Zong, Chengqing
Conference NameEMNLP
Conference Date2018-11
Conference PlaceBrussels, Belgium

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.

Document Type会议论文
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhu, Junnan,Li, Haoran,Liu, Tianshang,et al. MSMO: Multimodal Summarization with Multimodal Output[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
2018-JunnanZhu-emnlp(3625KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhu, Junnan]'s Articles
[Li, Haoran]'s Articles
[Liu, Tianshang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu, Junnan]'s Articles
[Li, Haoran]'s Articles
[Liu, Tianshang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu, Junnan]'s Articles
[Li, Haoran]'s Articles
[Liu, Tianshang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2018-JunnanZhu-emnlp.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.