Multi-document summarization aims to obtain core information from a
coll...
We consider the problem of eliciting compositional generalization
capabi...
We consider the problem of Open-world Information Extraction (Open-world...
Pairwise human judgments are pivotal in guiding large language models (L...
Traditional sentence embedding models encode sentences into vector
repre...
Researchers have proposed various information extraction (IE) techniques...
Aspect or query-based summarization has recently caught more attention, ...
Narrative summarization aims to produce a distilled version of a narrati...
Text segmentation is important for signaling a document's structure. Wit...
Abstractive summarization models typically learn to capture the salient
...
Podcasts have recently shown a rapid rise in popularity. Summarization o...
Comprehending a dialogue requires a model to capture diverse kinds of ke...
We propose a new approach to generate multiple variants of the target su...
We present implementation details of our abstractive summarizers that ac...
Amongst the best means to summarize is highlighting. In this paper, we a...
An abstract must not change the meaning of the original text. A single m...
Sentences produced by abstractive summarization systems can be ungrammat...
When writing a summary, humans tend to choose content from one or two
se...
Generating an abstract from a set of relevant documents remains challeng...
Seq2seq learning has produced promising results on summarization. Howeve...