Positioning yourself in the maze of Neural Text Generation: A Task-Agnostic Survey
It offers a comprehensive resource for researchers in natural language processing to understand and navigate the rapidly growing area of neural text generation.
The paper surveys fundamental components of neural text generation models across various tasks, providing a task-agnostic overview to help researchers position their work in the field.
Neural text generation metamorphosed into several critical natural language applications ranging from text completion to free form narrative generation. In order to progress research in text generation, it is critical to absorb the existing research works and position ourselves in this massively growing field. Specifically, this paper surveys the fundamental components of modeling approaches relaying task agnostic impacts across various generation tasks such as storytelling, summarization, translation etc., In this context, we present an abstraction of the imperative techniques with respect to learning paradigms, pretraining, modeling approaches, decoding and the key challenges outstanding in the field in each of them. Thereby, we deliver a one-stop destination for researchers in the field to facilitate a perspective on where to situate their work and how it impacts other closely related generation tasks.