ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization

TL;DR

This paper introduces ICAF, a novel framework that iteratively aligns images and texts using contrastive learning to improve multimodal abstractive summarization, outperforming existing methods on the MSMO dataset.

Contribution

The paper proposes an innovative iterative contrastive alignment framework with recurrent alignment and contrastive losses for better multimodal integration in summarization.

Findings

ICAF outperforms state-of-the-art baselines on MSMO dataset.

Recurrent alignment captures fine-grained semantic relationships.

Contrastive losses improve cross-modal embedding coherence.

Abstract

Integrating multimodal knowledge for abstractive summarization task is a work-in-progress research area, with present techniques inheriting fusion-then-generation paradigm. Due to semantic gaps between computer vision and natural language processing, current methods often treat multiple data points as separate objects and rely on attention mechanisms to search for connection in order to fuse together. In addition, missing awareness of cross-modal matching from many frameworks leads to performance reduction. To solve these two drawbacks, we propose an Iterative Contrastive Alignment Framework (ICAF) that uses recurrent alignment and contrast to capture the coherences between images and texts. Specifically, we design a recurrent alignment (RA) layer to gradually investigate fine-grained semantical relationships between image patches and text tokens. At each step during the encoding process, cross-modal contrastive losses are applied to directly optimize the embedding space. According to ROUGE, relevance scores, and human evaluation, our model outperforms the state-of-the-art baselines on MSMO dataset. Experiments on the applicability of our proposed framework and hyperparameters settings have been also conducted.