In this paper, we propose a novel neural single document extractive summarization model
for long documents, incorporating both the global context of the whole document and the …

Fine-tuning a large language model on downstream tasks has become a commonly adopted
process in the Natural Language Processing (NLP)(CITATION). However, such a process …

When searching for information, a human reader first glances over a document, spots
relevant sections, and then focuses on a few sentences for resolving her intention. However …

Document and discourse segmentation are two fundamental NLP tasks pertaining to
breaking up text into constituents, which are commonly used to help downstream tasks such …

Dialogue topic segmentation is critical in several dialogue modeling problems. However,
popular unsupervised approaches only exploit surface features in assessing topical …

This study proposes a two-stage method for variable-length abstractive summarization. This
is an improvement over previous models, in that the proposed approach can simultaneously …

Understanding discourse structures of news articles is vital to effectively contextualize the
occurrence of a news event. To enable computational modeling of news structures, we apply …

This paper proposes a transformer over transformer framework, called Transformer $^ 2$, to
perform neural text segmentation. It consists of two components: bottom-level sentence …

Text segmentation aims to uncover latent structure by dividing text from a document into
coherent sections. Where previous work on text segmentation considers the tasks of …

Natural Questions is a new challenging machine reading comprehension benchmark with
two-grained answers, which are a long answer (typically a paragraph) and a short answer …