PREMISE: Matching-based Prediction for Accurate Review Recommendation

TL;DR

PREMISE introduces a matching-based architecture for multimodal review helpfulness prediction, outperforming fusion-based methods by effectively capturing correlated content with lower computational cost.

Contribution

It proposes a novel matching-based approach that computes multi-scale, multi-field representations and filters semantics, improving multimodal review prediction accuracy.

Findings

Achieves superior performance on two datasets.

Requires less computational resources.

Outperforms state-of-the-art fusion methods.

Abstract

We present PREMISE (PREdict with Matching ScorEs), a new architecture for the matching-based learning in the multimodal fields for the multimodal review helpfulness (MRHP) task. Distinct to previous fusion-based methods which obtains multimodal representations via cross-modal attention for downstream tasks, PREMISE computes the multi-scale and multi-field representations, filters duplicated semantics, and then obtained a set of matching scores as feature vectors for the downstream recommendation task. This new architecture significantly boosts the performance for such multimodal tasks whose context matching content are highly correlated to the targets of that task, compared to the state-of-the-art fusion-based methods. Experimental results on two publicly available datasets show that PREMISE achieves promising performance with less computational cost.