Lin, Zijie and Liang, Bin and Long, Yunfei and Dang, Yixue and Yang, Min and Zhang, Min and Xu, Ruifeng (2022) Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis. In: 29th International Conference on Computational Linguistics, 2022-10-12 - 2022-10-17, Gyeongju, Republic of Korea.
Lin, Zijie and Liang, Bin and Long, Yunfei and Dang, Yixue and Yang, Min and Zhang, Min and Xu, Ruifeng (2022) Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis. In: 29th International Conference on Computational Linguistics, 2022-10-12 - 2022-10-17, Gyeongju, Republic of Korea.
Lin, Zijie and Liang, Bin and Long, Yunfei and Dang, Yixue and Yang, Min and Zhang, Min and Xu, Ruifeng (2022) Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis. In: 29th International Conference on Computational Linguistics, 2022-10-12 - 2022-10-17, Gyeongju, Republic of Korea.
Abstract
The existing research efforts in Multimodal Sentiment Analysis (MSA) have focused on developing the expressive ability of neural networks to fuse information from different modalities. However, these approaches lack a mechanism to understand the complex relations within and across different modalities, since some sentiments may be scattered in different modalities. To this end, in this paper, we propose a novel hierarchical graph contrastive learning (HGraph-CL) framework for MSA, aiming to explore the intricate relations of intra- and inter-modal representations for sentiment extraction. Specifically, regarding the intra-modal level, we build a unimodal graph for each modality representation to account for the modality-specific sentiment implications. Based on it, a graph contrastive learning strategy is adopted to explore the potential relations based on unimodal graph augmentations. Furthermore, we construct a multimodal graph of each instance based on the unimodal graphs to grasp the sentiment relations between different modalities. Then, in light of the multimodal augmentation graphs, a graph contrastive learning strategy over the inter-modal level is proposed to ulteriorly seek the possible graph structures for precisely learning sentiment relations. This essentially allows the framework to understand the appropriate graph structures for learning intricate relations among different modalities. Experimental results on two benchmark datasets show that the proposed framework outperforms the state-of-the-art baselines in MSA.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Uncontrolled Keywords: | Contrastive learning; Multimodality; Sentiment Analysis |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 03 Oct 2023 14:57 |
Last Modified: | 03 Oct 2023 14:58 |
URI: | http://repository.essex.ac.uk/id/eprint/34855 |
Available files
Filename: 2022.coling-1.622.pdf
Licence: Creative Commons: Attribution 4.0