This paper surveys the current state of the art in Natural Language Generation (NLG),
defined as the task of generating text or speech from non-linguistic input. A survey of NLG is …

Social media platforms provide active communication channels during mass convergence
and emergency events such as disasters caused by natural hazards. As a result, first …

Large language models (LLMs) have shown promise for automatic summarization but the
reasons behind their successes are poorly understood. By conducting a human evaluation …

It is well known that the standard likelihood training and approximate decoding objectives in
neural text generation models lead to less human-like responses for open-ended tasks such …

Contemporary works on abstractive text summarization have focused primarily on high-
resource languages like English, mostly due to the limited availability of datasets for low/mid …

Conditional language models are predominantly trained with maximum likelihood estimation
(MLE), giving probability mass to sparsely observed target sequences. While MLE trained …

We introduce extreme summarization, a new single-document summarization task which
does not favor extractive strategies and calls for an abstractive modeling approach. The idea …

Neural extractive summarization models usually employ a hierarchical encoder for
document encoding and they are trained using sentence-level labels, which are created …

Abstract Discriminative Correlation Filters (DCF) are efficient in visual tracking but suffer from
unwanted boundary effects. Spatially Regularized DCF (SRDCF) has been suggested to …

Single document summarization is the task of producing a shorter version of a document
while preserving its principal information content. In this paper we conceptualize extractive …