Self-Supervised Multimodal Opinion Summarization
Jinbae Im, Moonki Kim, Hoyeop Lee, Hyunsouk Cho, Sehee Chung
Abstract
Recently, opinion summarization, which is the generation of a summary from multiple reviews, has been conducted in a self-supervised manner by considering a sampled review as a pseudo summary. However, non-text data such as image and metadata related to reviews have been considered less often. To use the abundant information contained in non-text data, we propose a self-supervised multimodal opinion summarization framework called MultimodalSum. Our framework obtains a representation of each modality using a separate encoder for each modality, and the text decoder generates a summary. To resolve the inherent heterogeneity of multimodal data, we propose a multimodal training pipeline. We first pretrain the text encoder–decoder based solely on text modality data. Subsequently, we pretrain the non-text modality encoders by considering the pretrained text decoder as a pivot for the homogeneous representation of multimodal data. Finally, to fuse multimodal representations, we train the entire framework in an end-to-end manner. We demonstrate the superiority of MultimodalSum by conducting experiments on Yelp and Amazon datasets.- Anthology ID:
- 2021.acl-long.33
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 388–403
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.33
- DOI:
- 10.18653/v1/2021.acl-long.33
- Cite (ACL):
- Jinbae Im, Moonki Kim, Hoyeop Lee, Hyunsouk Cho, and Sehee Chung. 2021. Self-Supervised Multimodal Opinion Summarization. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 388–403, Online. Association for Computational Linguistics.
- Cite (Informal):
- Self-Supervised Multimodal Opinion Summarization (Im et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.acl-long.33.pdf