SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning

Wei Han, Hui Chen, Zhen Hai, Soujanya Poria, Lidong Bing


Abstract
With the boom of e-commerce, Multimodal Review Helpfulness Prediction (MRHP) that identifies the helpfulness score of multimodal product reviews has become a research hotspot. Previous work on this task focuses on attention-based modality fusion, information integration, and relation modeling, which primarily exposes the following drawbacks: 1) the model may fail to capture the really essential information due to its indiscriminate attention formulation; 2) lack appropriate modeling methods that takes full advantage of correlation among provided data. In this paper, we propose SANCL: Selective Attention and Natural Contrastive Learning for MRHP. SANCL adopts a probe-based strategy to enforce high attention weights on the regions of greater significance. It also constructs a contrastive learning framework based on natural matching properties in the dataset. Experimental results on two benchmark datasets with three categories show that SANCL achieves state-of-the-art baseline performance with lower memory consumption.
Anthology ID:
2022.coling-1.499
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5666–5677
Language:
URL:
https://aclanthology.org/2022.coling-1.499
DOI:
Bibkey:
Cite (ACL):
Wei Han, Hui Chen, Zhen Hai, Soujanya Poria, and Lidong Bing. 2022. SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5666–5677, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning (Han et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.499.pdf
Code
 declare-lab/sancl +  additional community code