Survey on Abstractive Text Summarization: Dataset, Models, and Metrics

TL;DR

This survey reviews recent advancements in abstractive text summarization, focusing on transformer-based models, datasets, evaluation metrics, and their strengths and limitations in producing human-like summaries.

Contribution

It provides a comprehensive overview of datasets, models, and metrics in abstractive summarization, highlighting recent transformer-based approaches and their performance.

Findings

Transformer models significantly improve summarization quality.

Evaluation metrics reveal strengths and limitations of current models.

Open-source code and datasets facilitate further research.

Abstract

The advancements in deep learning, particularly the introduction of transformers, have been pivotal in enhancing various natural language processing (NLP) tasks. These include text-to-text applications such as machine translation, text classification, and text summarization, as well as data-to-text tasks like response generation and image-to-text tasks such as captioning. Transformer models are distinguished by their attention mechanisms, pretraining on general knowledge, and fine-tuning for downstream tasks. This has led to significant improvements, particularly in abstractive summarization, where sections of a source document are paraphrased to produce summaries that closely resemble human expression. The effectiveness of these models is assessed using diverse metrics, encompassing techniques like semantic overlap and factual correctness. This survey examines the state of the art in text summarization models, with a specific focus on the abstractive summarization approach. It reviews various datasets and evaluation metrics used to measure model performance. Additionally, it includes the results of test cases using abstractive summarization models to underscore the advantages and limitations of contemporary transformer-based models. The source codes and the data are available at https://github.com/gospelnnadi/Text-Summarization-SOTA-Experiment.