Rapid growth of multi-modal documents on the Internet makes multi-modal summarization
research necessary. Most previous research summarizes texts or images separately. Recent …

The recent years have seen remarkable success in the use of deep neural networks on text
summarization. However, there is no clear understanding of\textit {why} they perform so well …

Contrastive learning models have achieved great success in unsupervised visual
representation learning, which maximize the similarities between feature representations of …

Neural models have become successful at producing abstractive summaries that are human-
readable and fluent. However, these models have two critical shortcomings: they often don't …

Abstractive summarization models are commonly trained using maximum likelihood
estimation, which assumes a deterministic (one-point) target distribution in which an ideal …

Automatic summarization generates concise summaries that contain key ideas of source
documents. As the most mainstream datasets for the news sub-domain, CNN/DailyMail and …

Text summarization aims at compressing long documents into a shorter form that conveys
the most important parts of the original document. Despite increased interest in the …

Researchers use figures to communicate rich, complex information in scientific papers. The
captions of these figures are critical to conveying effective messages. However, low-quality …

Reinforcement Learning (RL) based document summarisation systems yield state-of-the-art
performance in terms of ROUGE scores, because they directly use ROUGE as the rewards …

Attentional, RNN-based encoder-decoder models for abstractive summarization have
achieved good performance on short input and output sequences. For longer documents …