Due to the exponential growth of textual data and web sources, an automatic mechanism is required to identify relevant information embedded within them. The utility of Automatic Keyphrase Extraction (AKPE) cannot be overstated, given its widespread adoption in many Information Retrieval (IR), Natural Language Processing (NLP) and Text Mining (TM) applications, and its potential ability to solve difficulties related to extracting valuable information. In recent years, a wide range of AKPE techniques have been proposed. However, they are still impaired by low accuracy rates and moderate performance. This paper provides a comprehensive review of recent research efforts on the AKPE task and its related techniques. More concretely, we highlight the common process of this task, while also illustrating the various approaches used (supervised, unsupervised, and Deep Learning) and released techniques. We investigate the major challenges that such techniques face and depict the specific complexities they address. Besides, we provide a comparison study of the best performing techniques, discuss why some perform better than others and propose recommendations to improve each stage of the AKPE process.

中文翻译：

---

自动关键词提取：调查和趋势

由于文本数据和网络资源呈指数级增长，需要一种自动机制来识别嵌入其中的相关信息。自动关键短语提取 (AKPE) 的效用怎么强调都不为过，因为它在许多信息检索 (IR)、自然语言处理 (NLP) 和文本挖掘 (TM) 应用程序中被广泛采用，并且它具有解决与提取有价值的信息相关的困难的潜在能力信息。近年来，已经提出了广泛的 AKPE 技术。然而，它们仍然受到低准确率和中等性能的影响。本文全面回顾了最近关于 AKPE 任务及其相关技术的研究工作。更具体地说，我们强调了这项任务的共同过程，同时还说明了使用的各种方法（监督、无监督和深度学习）和发布的技术。我们调查了此类技术面临的主要挑战，并描述了它们解决的具体复杂性。此外，我们对最佳执行技术进行了比较研究，讨论了为什么有些技术比其他技术执行得更好，并提出了改进 AKPE 流程每个阶段的建议。