Starting from the concept, application scenarios and research significance of text filling, this paper divides text filling algorithms into two categories: traditional methods and deep learning, summarizes the development process of text filling algorithms in detail, focuses on describing the algorithm principles of text filling algorithms in recent years, and summarizes and evaluates text filling algorithms from the aspects of experimental results, advantages and disadvantages. In addition, this paper details the most commonly used text datasets and the most popular evaluation indicators - BLEU and Perplexity. Finally, this paper summarizes the research on text filling algorithm and looks forward to the future development trend. This paper aims to provide researchers with a comprehensive review of text filling algorithms to guide and prospect future development.
No takes yet. Share an insight, caveat, or question.
Cui et al. (2023) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: