Multi-Document Summarization By Sentence Extraction

By J. Goldstein, Vibhu Mittal, Jaime G. Carbonell, Mark Kantrowitz. 2000

449 citations recorded by the source corpus.

This paper discusses a text extraction approach to multi-document summarization that builds on single-document summarization methods by using additional, available information about the document set as a whole and the relationships between the documents. Multi-document summarization differs from single in that the issues of compression, speed, redundancy and passage selection are critical in the formation of useful summaries. Our approach addresses these issues by using domain-independent techniques based mainly on fast, statistical processing, a metric for reducing redundancy and maximizing diversity in the selected passages, and a modular framework to allow easy parameterization for different genres, corpora characteristics and user requirements.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/a79c4801090e7b6c1f31b83559f2d2b4af4b9c68

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

A Study of Global Inference Algorithms in Multi-document Summarization (2007, methodology): “In particular, we examine a standard paradigm where summaries are built by extracting relevant textual units from the documents [5, 10, 13, 20].”
An Empirical Analysis of NMT-Derived Interlingual Embeddings and Their Use in Parallel Sentence Identification (2017, background): “In multi-document summarisation [16] finding”
Recent automatic text summarization techniques: a survey (2016, background): “There are many issues like redundancy, temporal dimension, co-reference, sentence ordering, etc that need particular attention when summarizing multiple number of documents, thereby, making this task more complex (Goldstein et al. 2000).”
Multi-document Summarization via Deep Learning Techniques: A Survey (2020, methodology): “sion. The existing works using traditional algorithms can be divide into the following categories: term frequency-inverse document frequency (TF-IDF) based methods [10, 105], clustering based methods [42, 131], graph based methods [79, 130] and latent semantic analysis based methods [7, 46]. Deeplea”
Summarization Using Reinforcement Learning (2012, background): “One of the most well-known extractive approaches is maximal marginal relevance (MMR), which scores each textual unit and extracts the unit that has the highest score in terms of the MMR criteria (Goldstein et al., 2000).”
A Scalable Global Model for Summarization (2009, methodology): “Methods like McDonald’s, including the wellknown Maximal Marginal Relevance (MMR) algorithm (Goldstein et al., 2000), are subject to another problem: Summary-level redundancy is not”
Evaluation of Text Summarization in a Cross-lingual Information Retrieval Framework (2011, methodology): “When used in the context of MDS (Goldstein et al., 2000), text is segmented into passages (e.”
NCLS: Neural Cross-Lingual Summarization (2019, background): “Orasan and Chiorean (2008) summarize the Romanian news with the maximal marginal relevance method (Goldstein et al., 2000) and produce the English summaries for English speakers.”
Automatically Generating Wikipedia Articles: A Structure-Aware Approach (2009, methodology): “This strategy is commonly used in multi-document summarization (Barzilay et al., 1999; Goldstein et al., 2000; Radev et al., 2000), where the combination step eliminates the redundancy across selected excerpts.”
Evaluation of a Cross-lingual Romanian-English Multi-document Summariser (2008, methodology): “The method used here to produce summaries from clusters of related documents relies on the Maximal Marginal Relevance (MMR) method proposed in (Goldstein et al., 2000).”
SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization (2020, background): “(2014) develop evaluation heuristics inspired by the maximal marginal relevance metrics (Goldstein et al., 2000).”
BillSum: A Corpus for Automatic Summarization of US Legislation (2019, methodology): “To create the final summary, we apply the Maximal Marginal Relevance (MMR) algorithm (Goldstein et al., 2000).”
How to Compare Summarizers without Target Length? Pitfalls, Solutions and Re-Examination of the Neural Summarization Literature (2019, background): “Here is a list of the most cited ‘summarization’ papers of that period according to Google Scholar (Erkan and Radev, 2004; Radev et al., 2004; Gong and Liu, 2001; Conroy and O’leary, 2001; Lin and Hovy, 2000; Mihalcea, 2004; Goldstein et al., 2000).”