A Survey of Text Summarization Techniques

By Ani Nenkova, K. McKeown. Mining Text Data, 2012

616 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/8d7f6dc8b0b9101580cc96f1f303d1eba3d590af

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

XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages (2021, background): “…in Transformer-based models (Vaswani et al., 2017; Devlin et al., 2019) have rejuvenated abstractive text summarization (Rush et al., 2015; See et al., 2017; Zhang et al., 2020), which had previously received much less attention in comparison to extractive approaches (Nenkova and McKeown, 2012).”
APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning (2018, background): “With the rapid growth of text-based information on the Internet, automatic document summarisation attracts increasing research attention from the Natural Language Processing (NLP) community (Nenkova and McKeown, 2012).”
From Extractive to Abstractive Summarization: A Journey (2019, neutral): “But recent reports tend to suggest that advances in extractive text summarization have slowed down in the past few years (Nenkova and McKeown, 2012).”
SUM-QE: a BERT-based Summary Quality Estimation Model (2019, neutral): “uation metric (Nenkova and McKeown, 2012; Allahyari et al., 2017; Gambhir and Gupta, 2017).”
Assessing sentence scoring techniques for extractive text summarization (2013, methodology): “It is important to notice that Lloret and Palomar (2012) and Nenkova and McKeown (2012) present two recent and comprehensive surveys on text summarization.”
HEADS: Headline Generation as Sequence Prediction Using an Abstract Feature-Rich Space (2015, background): “…ob-jective of text summarization is to produce a para-graph or abstract that summarizes a rather large collection of texts (Mani and Maybury, 1999; Das and Martins, 2007; Nenkova and McKeown, 2012), the task of producing a very short summary comprised of 10–15 words has also been broadly studied.”
Intrinsic Evaluation of Summarization Datasets (2020, background): “8077 sequent work (Radev et al., 2002; Nenkova, 2006; Nenkova and McKeown, 2012; Peyrard, 2019a) that refined and extended these properties.”
Trains of thought: generating information maps (2012, methodology): “In the summarization task [14, 2, 15], the goal is often to summarize a corpus of texts by extracting a list of sentences.”
Recent advances in document summarization (2017, background): “We aim at a self-contained2 description of the latest research progress for document summarization made roughly from 2011, as a solid complement of previous comprehensive reviews [39,137,139] written earlier than that.”
Multi-document Summarization via Deep Learning Techniques: A Survey (2020, background): “on traditional algorithms instead of deep learning based methods [36, 47, 92, 116].”
Cooperative Generator-Discriminator Networks for Abstractive Summarization with Narrative Flow (2019, result): “Our study contrasts with most previous work that focused on either ex-tractive document-level summarization (Nenkova and McKeown, 2012; Allahyari et al., 2017) or abstractive sentence-level summarization (Rush et al., 2015; Grusky et al., 2019; Narayan et al., 2018a), where maintaining a good…”
Identiﬁcation and Characterization of Newsworthy Verbs in World News (background): “…systems work only with indicators of importance coming solely from the input to be summarized, or possibly also from the context of the input, i.e . analyzing the anchor text of links to a webpage, or comments on a blog post or citations to a scientiﬁc article (Nenkova and McKeown, 2012).”
Tool Learning with Foundation Models (2023, neutral): “Prior to this breakthrough, NLP was a challenging field that necessitated designing separate learning objectives for distinct research domains, such as dependency parsing (Kübler et al., 2009), named entity recognition (Nadeau & Sekine, 2007), and summarization (Nenkova & McKeown, 2012).”
Distraction-Based Neural Networks for Modeling Document (2016, methodology): “Neural summarization models Automatic summarization has been intensively studied for both text [Mani, 2001; Das and Martins, 2007; Nenkova and McKeown, 2013] and speech [Zhu and Penn, 2006; Zhu et al., 2010] .”
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).”
Text Summarization Techniques: A Brief Survey (2017, methodology): “In order to better understand how summarization systems work, we describe three fairly independent tasks which all summarizers perform [46]: 1 ) Construct an intermediate representation of the input text which expresses the main aspects of the text.”