Knowledge Commons of Institute of Automation,CAS
Multimodal Summarization with Guidance of Multimodal Reference | |
Zhu, Junnan1,2; Zhou, Yu1,2; Zhang, Jiajun1,2; Li, Haoran4; Zong, Chengqing1,2,3; Li, Zhangliang5 | |
2020-02 | |
会议名称 | The Thirty-Fourth AAAI Conference on Artificial Intelligence |
会议日期 | 2020.2.7-2020.2.12 |
会议地点 | New York, USA |
会议录编者/会议主办者 | Association for Computational Linguistics |
出版者 | Association for Computational Linguistics |
摘要 | Multimodal summarization with multimodal output (MSMO) is to generate a multimodal summary for a multimodal news report, which has been proven to effectively improve users' satisfaction. The existing MSMO methods are trained by the target of text modality, leading to the modality-bias problem that ignores the quality of model-selected image during training. To alleviate this problem, we propose a multimodal objective function with the guidance of multimodal reference to use the loss from the summary generation and the image selection. Due to the lack of multimodal reference data, we present two strategies, i.e., ROUGE-ranking and Orderranking, to construct the multimodal reference by extending the text reference. Meanwhile, to better evaluate multimodal outputs, we propose a novel evaluation metric based on joint multimodal representation, projecting the model output and multimodal reference into a joint semantic space during evaluation. Experimental results have shown that our proposed model achieves the new state-of-the-art on both automatic and manual evaluation metrics. Besides, our proposed evaluation method can effectively improve the correlation with human judgments. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 自然语言处理 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39084 |
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 | Zhou, Yu |
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 4.JD AI Research 5.Kingsoft AI Lab |
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,Zhou, Yu,Zhang, Jiajun,et al. Multimodal Summarization with Guidance of Multimodal Reference[C]//Association for Computational Linguistics:Association for Computational Linguistics,2020. |
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 | ||
AAAI-ZhuJ.1133.pdf(954KB) | 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