Centroid-based summarization of multiple documents

By Dragomir R. Radev, Hongyan Jing, Magorzata Sty, Daniel Tam. Information Processing & Management, 2004

1,272 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/fdc279eddcd4ebdaa42a46bfa20a6aba8d32e597

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking (2019, background): “Previously, unsupervised learning has been widely applied to extractive approaches (Radev et al., 2004; Mihalcea and Tarau, 2004).”
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization (2018, methodology): “Centroid-based methods try to select sentences such that the resulting summary is close to the centroid of the input documents in the representation space (Radev et al., 2004).”
A Survey on Automatic Text Summarization (2007, methodology): “The two metrics are used directly for evaluation (see (Radev et al., 2004) for more details).”
MEAD - A Platform for Multidocument Multilingual Text Summarization (2004, background): “• Centroid: cosine overlap with the centroid vector of the cluster (Radev et al., 2004), • SimWithFirst: cosine overlap with the first sentence in the document (or with the title, if it exists), • Length: 1 if the length of the sentence is above a given threshold and 0 otherwise, • RealLength: the…”
Multi-Document Summarization Using Cross-Language Texts (2004, methodology): “Second, considering multiple documents, we construct a global term cluster [3].”
Benchmarking Large Language Models for News Summarization (2023, background): “CNN/DM includes articles from the CNN and DailyMail websites as the source article and adapt the bullet point highlights that come with the website articles as reference summaries.”
Explaining anomalies detected by autoencoders using Shapley Additive Explanations (2021, methodology): “A popular explanation method is the representation of a cluster of points by their centroid or by a set of distant points in the cluster[17].”
A new sentence similarity measure and sentence based extractive technique for automatic text summarization (2009, methodology): “The centroid-based method (Erkan & Radev, 2004; Radev et al., 2004) is one of the most popular extractive summarization methods .”
Multi-document summarization using cluster-based link analysis (2008, methodology): “The centroid-based method [23] is one of the most popular extractive summarization methods.”
Cross-Language Document Summarization Based on Machine Translation Quality Prediction (2010, methodology): “For multi-document summarization, the centroid-based method (Radev et al., 2004) is a typical method, and it scores sentences based on cluster centroids, position and TFIDF features.”
Graph-based Neural Multi-Document Summarization (2017, background): “Centroid (Radev et al., 2004b) 36.”
AgreeSum: Agreement-Oriented Multi-Document Summarization (2021, background): “The attempted non-neural models rely heavily on topic/theme detection and tracking, and are more extractive than abstractive (Radev et al., 2004).”
Recent advances in document summarization (2017, background): “In a single document, summary information can be presented by preserving the order in the original document [157].”
Aspect-Controllable Opinion Summarization (2021, methodology): “Traditional extractive systems include selecting as a summary the review closest to the C ENTROID (Radev et al., 2004) of the input reviews and L EX R ANK (Erkan and Radev, 2004), a PageRank-like algorithm that selects the most salient sentences from the input.”