MAST: Multimodal Abstractive Summarization with Trimodal Hierarchical Attention
TL
TL;DR
A new model for Multimodal Abstractive Text Summarization that utilizes information from all three modalities – text, audio and video – in a multimodal video and presents a sequence-to-sequence trimodal hierarchical attention-based model that overcomes challenges by letting the model pay more attention to the text modality.
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.
References32 items
1
GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples
2
Multimodal Summarization with Guidance of Multimodal Reference
3
Text Summarization with Pretrained Encoders
4
Multimodal Abstractive Summarization for How2 Videos
5