The Automatic Creation of Literature Abstracts

By H. P. Luhn. 1958

How researchers see this paper

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

In Summarization

Citations in the corpus

Controllable Abstractive Summarization (2017, background): “Automatic summarization has been an active ﬁeld of research for close to 60 years (Luhn, 1958).”
LexRank: Graph-based Lexical Centrality as Salience in Text Summarization (2004, background): “Early research on extractive summarization is based on simple heuristic features of the sentences such as their position in the text, the overall frequency of the words they contain, or some key phrases indicating the importance of the sentences (Baxendale, 1958; Edmundson, 1969; Luhn, 1958).”
Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation (2003, background): “…1995; Mann et al., 1992; Teufel and Moens, 1997; Zechner, 1995), processing of structured templates (Paice and Jones, 1993), sentence compression (Hori et al., 2002; Knight and Marcu, 2001; Grefenstette, 1998, Luhn, 1958), and generation of abstracts from multiple sources (Radev and McKeown, 1998).”
LCSTS: A Large Scale Chinese Short Text Summarization Dataset (2015, background): “…most researches are related to extractive summarizations by analyzing the organization of the words in the document (Nenkova and McKeown, 2011) (Luhn, 1998); Since it needs labeled data sets for supervised machine learning methods and labeling dataset is very intensive, some researches focused…”
Neural Document Summarization by Jointly Learning to Score and Select Sentences (2018, methodology): “In these methods, many surface features are useful, such as term frequency (Luhn, 1958), TF*IDF weights (Erkan and Radev, 2004), sentence length (Cao et al., 2015a) and sentence positions (Ren et al., 2017).”
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.”
Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features (2017, background): “profile seems to roughly follow Luhn’s hypothesis (Luhn, 1958), a well known information retrieval paradigm, stating that mid-rank terms are the most significant to discriminate content.”
Headline Generation Based on Statistical Translation (2000, background): “Most previous work on summarization focused on extractive methods, investigating issues such as cue phrases (Luhn, 1958), positional indicators (Edmundson, 1964), lexical occurrence statistics (Mathis et al., 1973), probabilistic measures for token salience (Salton et al., 1997), and the use of…”
Planning with Learned Entity Prompts for Abstractive Summarization (2021, methodology): “…source text, such as Rhetorical Structure Theory (RST; Mann and Thompson, 1988) or MUC-style representations (McKeown and Radev, 1995) to interpret the source texts, while others used a shallow semantic analysis using only word frequency (Luhn, 1958) or lexical chains (Barzilay and Elhadad, 1997).”
Text summarization using unsupervised deep learning (2017, methodology): “The early technique to address with manual text summarization dates back as early as 1958 (Luhn, 1958) and the proposed techniques were reviewed extensively (Lloret and Palomar, 2012; Nenkova and McKeown, 2012).”
A Survey of Text Summarization Techniques (2012, background): “In remarkably early work on text summarization [53], Luhn proposed the use of frequency thresholds to identify descriptive words in a document to be summarized, a simple representation of the document’s topic.”
A New Approach to Improving Multilingual Summarization Using a Genetic Algorithm (2010, background): “Considered the ﬁrst work on sentence scoring for automated text summarization, Luhn (1958) based the signiﬁcance factor of a sentence on the frequency and the relative positions of signiﬁ-cant words within a sentence.”
Termite: visualization techniques for assessing textual topic models (2012, background): “Assessing topical composition typically requires examining only a subset of the common or mid-frequency words [17], and does not require seriating the full vocabulary.”
Learning Algorithms for Keyphrase Extraction (2000, background): “Several papers explore the task of producing a summary of a document by extracting key sentences from the document (Luhn, 1958; Edmundson, 1969; Marsh et al., 1984; Paice, 1990; Paice and Jones, 1993; Johnson et al., 1993; Salton et al., 1994; Kupiec et al., 1995; Brandow et al., 1995; Jang and…”
A Supervised Approach to Extractive Summarisation of Scientific Papers (2017, background): “word frequency (Luhn, 1958), location in the document (Baxendale, 1958), and TF-IDF (Salton et al.”
Main Core Retention on Graph-of-Words for Single-Document Keyword Extraction (2015, background): “Indeed, Luhn in [17], which is one of the earliest works in automatic summarization, capitalizes on the term frequency to first extract the most salient keywords before using them to detect sentences.”
Interpreting TF-IDF term weights as making relevance decisions (2008, background): “Instead, the term-frequency factor was originally thought to be indicative of document topic [Luhn 1958], and the inverse document-frequency (IDF) is reasoned [Spärck Jones 1972] on the basis of Zipf law.”