MSMO: Multimodal Summarization with Multimodal Output
Junnan Zhu, Haoran Li, Tianshang Liu, Yu Zhou, Jiajun Zhang, Chengqing Zong
Abstract
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 intra-modality salience and inter-modality relevance. The experimental results show the effectiveness of MMAE.- Anthology ID:
- D18-1448
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4154–4164
- Language:
- URL:
- https://aclanthology.org/D18-1448
- DOI:
- 10.18653/v1/D18-1448
- Cite (ACL):
- Junnan Zhu, Haoran Li, Tianshang Liu, Yu Zhou, Jiajun Zhang, and Chengqing Zong. 2018. MSMO: Multimodal Summarization with Multimodal Output. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4154–4164, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- MSMO: Multimodal Summarization with Multimodal Output (Zhu et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/D18-1448.pdf