CLAILGMay 27, 2021

Self-Supervised Multimodal Opinion Summarization

arXiv:2105.13135v1718 citations
Originality Incremental advance
AI Analysis

This work addresses opinion summarization for users and businesses by integrating multimodal data, though it is incremental as it builds on existing self-supervised text-based methods.

The paper tackles the problem of generating summaries from multiple reviews by incorporating non-text data like images and metadata, proposing a self-supervised multimodal framework called MultimodalSum that achieves superior performance on Yelp and Amazon datasets.

Recently, opinion summarization, which is the generation of a summary from multiple reviews, has been conducted in a self-supervised manner by considering a sampled review as a pseudo summary. However, non-text data such as image and metadata related to reviews have been considered less often. To use the abundant information contained in non-text data, we propose a self-supervised multimodal opinion summarization framework called MultimodalSum. Our framework obtains a representation of each modality using a separate encoder for each modality, and the text decoder generates a summary. To resolve the inherent heterogeneity of multimodal data, we propose a multimodal training pipeline. We first pretrain the text encoder--decoder based solely on text modality data. Subsequently, we pretrain the non-text modality encoders by considering the pretrained text decoder as a pivot for the homogeneous representation of multimodal data. Finally, to fuse multimodal representations, we train the entire framework in an end-to-end manner. We demonstrate the superiority of MultimodalSum by conducting experiments on Yelp and Amazon datasets.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes