pith. sign in

arxiv: 2209.05040 · v5 · pith:5N2GS2TUnew · submitted 2022-09-12 · 💻 cs.CL · cs.AI

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

classification 💻 cs.CL cs.AI
keywords attentionsanclcontrastivehelpfulnesslearningnaturalinformationmodeling
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions

    cs.CL 2022-11 unverdicted novelty 5.0

    Multimodal contrastive learning with adaptive weighting and interaction module achieves state-of-the-art results on two MRHP benchmark datasets.

  2. Bounded-Compute Multimodal Regression for Product-Rating Prediction

    cs.CV 2026-05 unverdicted novelty 3.0

    Adapts SmolVLM2-256M-Video-Instruct for product-rating regression via MLP on decoder states, reporting 0.39 PLCC and 0.40 CES on official evaluation.