@inproceedings{khullar-arora-2020-mast,
    title = "{MAST}: Multimodal Abstractive Summarization with Trimodal Hierarchical Attention",
    author = "Khullar, Aman  and
      Arora, Udit",
    editor = "Castellucci, Giuseppe  and
      Filice, Simone  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Specia, Lucia",
    booktitle = "Proceedings of the First International Workshop on Natural Language Processing Beyond Text",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.nlpbt-1.7/",
    doi = "10.18653/v1/2020.nlpbt-1.7",
    pages = "60--69",
    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."
}