Many military communication domains involve rapidly conveying situation awareness with few words.
In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization.
We present an empirical study in favor of a cascade architecture to neural text summarization.
The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts.
We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences.
If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged.
Ranked #23 on Text Summarization on GigaWord
While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences.
There is thus a crucial gap between sentence selection and fusion to support summarizing by both compressing single sentences and fusing pairs.
The most important obstacles facing multi-document summarization include excessive redundancy in source descriptions and the looming shortage of training data.
Generating an abstract from a collection of documents is a desirable capability for many real-world applications.