The Impact of Frequency on Summarization

By Ani Nenkova, Lucy Vanderwende. 2005

341 citations recorded by the source corpus.

Subfields: Natural Language Processing, Evaluation & Benchmarks

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

In Evaluation & Benchmarks

Citations in the corpus

Generating Wikipedia by Summarizing Long Sequences (2018, methodology): “SumBasic (Nenkova & Vanderwende, 2005): Word frequencies in the input text are used to assign scores to words, which are in turn used to score sentences.”
Big Bird: Transformers for Longer Sequences (2020, background): “[69] A.”
A Simple, Fast Diverse Decoding Algorithm for Neural Generation (2016, methodology): “For reranking, we employ various global features taken from or inspired by pre-neural work in summarization (Daumé III and Marcu, 2006; Nenkova and Vanderwende, 2005; McKeown et al., 1999).”
BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization (2019, positive): “For L EX R ANK and S UM B ASIC , we used sumy 8 .”
Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures (2016, methodology): “…problem, recent models have been developed that are extensions of multimodal spaces; they are able to not only rank sentences, but can also generate them (Chen & Zitnick, 2015; Donahue et al., 2015; Karpathy & Fei-Fei, 2015; Kiros et al., 2015; Lebret et al., 2015; Mao et al., 2015a; Vinyals et…”
Improving the Estimation of Word Importance for News Multi-Document Summarization - Extended Technical Report (2016, background): “The simplest but competitive way to do this task is to estimate the word probability from the input (Nenkova and Vanderwende, 2005).”
Exploring Content Models for Multi-Document Summarization (2009, methodology): “Beginning with a simple word frequency based model (Nenkova and Vanderwende, 2005), we construct a sequence of models each injecting more structure into the representation of document set content and exhibiting ROUGE gains along the way.”
A Scalable Global Model for Summarization (2009, methodology): “The general idea of concept-level scoring for summarization is employed in the SumBasic system (Nenkova and Vanderwende, 2005), which chooses sentences greedily according to the sum of their word values (values are derived from fre-”
Automatic Caption Generation for News Images (2013, background): “Existing document content representations include simple unigram frequencies (Nenkova and Vanderwende, 2005; Vanderwende et al., 2007; Haghighi and Vanderwende, 2009), syntactic features (such as clause information or dependencies) (Barzilay and McKeown, 2005), and topic representations (Daumé III a”
Improving the Estimation of Word Importance for News Multi-Document Summarization (2014, background): “The simplest but competitive way to do this task is to estimate the word probability from the input (Nenkova and Vanderwende, 2005).”
SemEval-2015 Task 1: Paraphrase and Semantic Similarity in Twitter (PIT) (2015, methodology): “We employ the scoring method used in SumBasic (Nenkova and Vander-wende, 2005; Vanderwende et al., 2007), a simple but powerful summarization system, to ﬁnd salient sentences.”
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).”
Jointly Learning to Extract and Compress (2011, methodology): “…redundancy (Carbonell and Goldstein, 1998), recent methods show greater success by using a simpler notion of coverage: bigrams contribute content, and redundancy is implicitly encoded in the fact that redundant sentences cover fewer bigrams (Nenkova and Vanderwende, 2005; Gillick and Favre, 2009).”
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization (2018, background): “Sentences may be selected based on scores computed from the presence of topic-words or word-frequencies (Nenkova & Vanderwende, 2005).”
Nonparametric Method for Data-driven Image Captioning (2014, neutral): “Figure 1: BLEU scores vs k for SumBasic extraction.”
Towards Content Transfer through Grounded Text Generation (2019, neutral): “sentences (Nenkova and Vanderwende, 2005).”