MAST: Multimodal Abstractive Summarization with Trimodal Hierarchical Attention

TL;DR

MAST is a novel multimodal abstractive summarization model that integrates text, audio, and video information using hierarchical attention, significantly improving summarization performance on the How2 dataset.

Contribution

This work introduces a trimodal hierarchical attention model that effectively incorporates audio alongside text and video for improved summarization.

Findings

MAST outperforms previous models by 2.51 points in Content F1 score.

MAST achieves a 1.00 point improvement in Rouge-L score.

The model demonstrates the usefulness of audio modality in multimodal summarization.

Abstract

This paper presents MAST, a new model for Multimodal Abstractive Text Summarization that utilizes information from all three modalities -- text, audio and video -- in a multimodal video. Prior work on multimodal abstractive text summarization only utilized information from the text and video modalities. We examine the usefulness and challenges of deriving information from the audio modality and present a sequence-to-sequence trimodal hierarchical attention-based model that overcomes these challenges by letting the model pay more attention to the text modality. MAST outperforms the current state of the art model (video-text) by 2.51 points in terms of Content F1 score and 1.00 points in terms of Rouge-L score on the How2 dataset for multimodal language understanding.