What is it about?
Figurative language generation (FLG) is the task of reformulating a given text to include a desired figure of speech, such as a hyperbole, a simile, and several others, while still being faithful to the original context. This can advance the goal of machines being able to write in different figures of speech, which has a wide range of applications, mainly divided into two categories: aiding in various downstream Natural Language Processing tasks and supporting the development of application products such as educational systems. Our survey provides a systematic overview of the development of FLG, mostly in English, starting with the description of some common figures of speech, their corresponding generation tasks and datasets. We then focus on various modelling approaches and assessment strategies, leading us to discussing some challenges in this field, and suggesting some potential directions for future research.
Featured Image
Photo by Aaron Burden on Unsplash
Why is it important?
This is the first survey that summarizes the progress of FLG including the most recent development in Natural Language Processing.
Perspectives
I hope this survey can help people to easily track the machine writing frontier and understand the development and impact of the field.
Huiyuan Lai
University of Groningen
Read the Original
This page is a summary of: A Survey on Automatic Generation of Figurative Language: From Rule-based Systems to Large Language Models, ACM Computing Surveys, March 2024, ACM (Association for Computing Machinery),
DOI: 10.1145/3654795.
You can read the full text:
Resources
Contributors
The following have contributed to this page
