A comprehensive review of automatic text summarization techniques: method, data, evaluation and coding

TL;DR

This paper offers a comprehensive literature review of automatic text summarization techniques, covering methods, datasets, evaluation metrics, and empirical analysis using the CNN Corpus dataset.

Contribution

It systematically organizes ATS approaches based on their mechanisms and provides an extensive review of datasets and evaluation methods, including empirical comparisons.

Findings

Diverse ATS methods are categorized by their summarization mechanisms.

Extensive review of datasets and evaluation techniques for ATS.

Empirical analysis using CNN Corpus dataset compares extractive and abstractive methods.

Abstract

We provide a literature review about Automatic Text Summarization (ATS) systems. We consider a citation-based approach. We start with some popular and well-known papers that we have in hand about each topic we want to cover and we have tracked the "backward citations" (papers that are cited by the set of papers we knew beforehand) and the "forward citations" (newer papers that cite the set of papers we knew beforehand). In order to organize the different methods, we present the diverse approaches to ATS guided by the mechanisms they use to generate a summary. Besides presenting the methods, we also present an extensive review of the datasets available for summarization tasks and the methods used to evaluate the quality of the summaries. Finally, we present an empirical exploration of these methods using the CNN Corpus dataset that provides golden summaries for extractive and abstractive methods.