MASCA: A Multimodal Abstractive Summarization Model Based on Core Words Fusion Attention

Multimodal Abstractive Summarization using bidirectional encoder representations from transformers with attention mechanism

“…Yin et al [ 27 ] proposed the MASCA model, which used text and pictures as input modeling to generate a summary. They provide attention to the information contained in original data by introducing core words fusion attention.…”