综述抽象文本摘要的最新进展，涵盖数据集、模型与评估方法。
Survey on Abstractive Text Summarization: Dataset, Models, and Metrics
- 系统梳理抽象摘要的主流模型与技术路径
- 对比分析多个数据集与评估指标的效果差异
- 适合从事NLP摘要研究或模型选型的研究者参考
深度学习的进展，尤其是变压器（transformer）的引入，显著提升了自然语言处理（NLP）多项任务的表现，包括机器翻译、文本分类和文本摘要等文本到文本任务，以及响应生成、图像描述等数据到文本任务。变压器模型以注意力机制、通用知识预训练和下游任务微调为特点，尤其在抽象摘要任务中表现突出，能对原文内容进行重述，生成接近人类表达的摘要。模型效果通过多种评估指标衡量，包括语义重叠和事实正确性等。本综述聚焦抽象摘要领域，回顾当前主流数据集与评估方法，并通过测试案例展示现有基于Transformer模型的优势与局限。源代码与数据可从 https://github.com/gospelnnadi/Text-Summarization-SOTA-Experiment 获取。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。