Generic text summarization using relevance measure and latent semantic analysis

By Yihong Gong, Xin Liu. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2001

963 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/118605693bb5c1846915e967fdb8383ecac13c70

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 New Approach to Improving Multilingual Summarization Using a Genetic Algorithm (2010, methodology): “Gong and Liu (2001) and Steinberger and Jezek (2004) used singular value decomposition (SVD) to generate extracts.”
Automatic generic document summarization based on non-negative matrix factorization (2009, methodology): “This method decomposes matrix A into three matrices, U, D, and VT (Gong & Liu, 2001).”
A Survey of Text Summarization Techniques (2012, background): “The original proposal of Gong and Liu was to select one sentence for each of the most important topics.”
Natural language processing: state of the art, current trends and challenges (2017, background): “Summaries can also be of two types: generic or query-focused (Gong and Liu 2001 [50]; Dunlavy et al. 2007 [37]; Wan 2008 [144]; Ouyang et al. 2011 [99]).”
On the Use of Automated Text Summarization Techniques for Summarizing Source Code (2010, methodology): “We identified the three combinations that perform the best in natural language summarization: log , tf-idf , and binary-entropy , for both LSI [6-7, For generating a summary using VSM, the terms in the document (i.e., class or method) are ordered according to the chosen weight and the top K terms…”
Generic summarization and keyphrase extraction using mutual reinforcement principle and sentence clustering (2002, background): “In addition, there is also a great amount of news articles and broadcast transcripts generated daily from various news agencies needing e.ective summarization.”
Recent automatic text summarization techniques: a survey (2016, background): “Summaries can also be of two types: generic or query-focused (Gong and Liu 2001; Dunlavy et al. 2007; Wan 2008; Ouyang et al. 2011).”
Using Mechanical Turk to Create a Corpus of Arabic Summaries (2010, methodology): “(Steinberger and Ježek, 2004; Gong and Liu, 2001).”
Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization (2008, methodology): “(cid:15) LSA : conducts latent semantic analysis on terms by sentences matrix as proposed in [12].”
BillSum: A Corpus for Automatic Summarization of US Legislation (2019, methodology): “In addition, we evaluate the following unsupervised baselines: SumBasic (Nenkova and Vanderwende, 2005), Latent Semantic Analysis (LSA) (Gong and Liu, 2001) and TextRank (Mihalcea and Tarau, 2004).”
BanditSum: Extractive Summarization as a Contextual Bandit (2018, methodology): “Recently, neural network-based meth-ods have been gaining popularity over classical methods (Luhn, 1958; Gong and Liu, 2001; Con-roy and O’leary, 2001; Mihalcea and Tarau, 2004; Wong et al., 2008), as they have demonstrated stronger performance on large corpora.”
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).”
Event Summarization Using Tweets (2011, background): “This is due to the fact that while twitter users are remarkably consistent on how they refer to plays such as touchdowns and field-goals, there is a much larger variability when they refer to details such number of yards gained or names of players involved.”