Recent automatic text summarization techniques: a survey

By Mahak Gambhir, Vishal Gupta. 2016

739 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Summarization

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

In Summarization

Citations in the corpus

LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization (2019, positive): “Different from extractive text summarization (Gambhir and Gupta, 2017; Nallapati et al., 2017; Verma and Lee, 2017), NATS relies on modern deep learning models, particularly sequence-to-sequence (Seq2Seq) models, to generate words from a vocabulary based on the representations/features of source doc”
Global Voices: Crossing Borders in Automatic News Summarization (2019, background): “Despite the fast development of automatic summarization (Allahyari et al., 2017; Dong, 2018; Gambhir and Gupta, 2017), present technology mostly focuses on monolingual summarization.”
Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts (2018, background): “However, abstractive summarization for dialogue/meeting summarization has not yet explored due to the lack of suitable benchmark data [21], because the benchmark dialogue data is only annotated with the importance of utterances without abstractive summaries [22].”
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).”
Recent advances in document summarization (2017, background): “There exist very few similar attempts (such as [54]) that unfortunately fail to cover the most significant study trends or are in shortage of clear organization of content, which partly motivates us for writing this survey for recent studies.”