Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources

By Krysta Marie Svore, Lucy Vanderwende, C. Burges. 2007

254 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension (2018, background): “In addition, news providers such as CNN and Daily Mail supplement their articles with a number of bullet points (Svore et al., 2007; Woodsend and Lapata, 2010; Hermann et al., 2015), which out-line the highlights of the news and hence form a supplemental source for generating passages.”
Neural Summarization by Extracting Sentences and Words (2016, neutral): “One stumbling block to applying neural network models to extractive summarization is the lack of training data, i.e., documents with sentences (and words) labeled as summary-worthy.”
Ranking Sentences for Extractive Summarization with Reinforcement Learning (2018, methodology): “An alternative method (Svore et al., 2007; Cao et al., 2016; Nallapati et al., 2017) identifies the set of sentences which collectively gives the highest ROUGE with respect to the gold summary.”
A new sentence similarity measure and sentence based extractive technique for automatic text summarization (2009, methodology): “Comparison our methods with four methods CRF, NetSum, Manifold–Ranking and SVM are shown in Tables 3 and 4.”
Text summarization using unsupervised deep learning (2017, background): “Also, Svore et al. (2007) proposed a neural network-based system, called NetSum.”
A Survey on Automatic Text Summarization (2007, methodology): “Svore et al. (2007) propose an algorithm based on neural nets and the use of third party datasets to tackle the problem of extractive summarization, outperforming the baseline with statistical significance.”
Automatic Generation of Story Highlights (2010, methodology): “Importantly, they represent the gist of the entire document and thus often differ substantially from the ﬁrst n sentences in the article (Svore et al., 2007).”
Neural Extractive Summarization with Side Information (2017, methodology): “5 Our dataset is an evolved version of the CNN dataset ﬁrst collected by Svore, Vanderwende, and Burges (2007) for highlight generation.”