SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning
Han, Wei, Chen, Hui, Hai, Zhen, Poria, Soujanya, Bing, Lidong
–arXiv.org Artificial Intelligence
With the boom of e-commerce, Multimodal Review Helpfulness Prediction (MRHP), which aims to sort product reviews according to the predicted helpfulness scores 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 take 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.
arXiv.org Artificial Intelligence
Oct-5-2022
- Country:
- Genre:
- Research Report (1.00)
- Industry:
- Information Technology > Services > e-Commerce Services (0.34)
- Technology: