论文标题
将自己定位在神经文本生成的迷宫中：一项任务不合时宜的调查
Positioning yourself in the maze of Neural Text Generation: A Task-Agnostic Survey
论文作者
论文摘要
神经文本生成变成了几种关键的自然语言应用，从文本完成到自由形式的叙事产生。为了在文本生成中进行研究，吸收现有的研究工作并将自己定位在这个大规模增长的领域至关重要。具体而言，本文调查了建模方法的基本组成部分，涉及诸如讲故事，摘要，翻译等各种任务的任务不可思议的影响，在这种情况下，我们介绍了对学习范式，预处理，建模方法，解码和钥匙挑战在每个领域中均出色的领域的命令技术的抽象。因此，我们为该领域的研究人员提供了一个一站式目的地，以促进对位置的位置以及它如何影响其他紧密相关的一代任务的观点。
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.
