Exploring the Landscape of Automatic Text Summarization: A Comprehensive Survey

Abstract

The discipline of Automatic Text Summarization (ATS), which is expanding quickly, intends to automatically create summaries of enormous amounts of text so that readers can save time and effort. ATS is a rapidly growing field that aims to save readers time and effort by automatically generating summaries of large volumes of text. In recent years, significant advancements have been witnessed in this area, accompanied by challenges that have spurred extensive research. The proliferation of textual data has sparked substantial interest in ATS, which is thoroughly examined in this survey study. Researchers have been refining ATS techniques since the 1950s, primarily categorized as extractive, abstractive, or hybrid approaches. In the extractive approach, key sentences are extracted from the source document(s) and combined to form the summary, while the abstractive approach employs an intermediary representation of the input document(s) to generate a summary that may differ from the original text. Hybrid approaches combine elements of both extractive and abstractive methods. Despite various recommended methodologies, the generated summaries still exhibit noticeable differences compared to those created by humans. This research survey offers an inclusive exploration of ATS, covering its challenges, types, classifications, approaches, applications, methods, implementations, processing and preprocessing techniques, linguistic analysis, datasets, and evaluation measures, catering to the needs of researchers in the field.

Keywords

• Automatic text summarization
• text summarization challenges
• text summarization methods
• text summarization datasets
• text summarization evaluation measures