arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.15780cs.CLcs.AIcs.LG
收藏

神经语言生成:公式化、方法和评估

Neural Language Generation: Formulation, Methods, and Evaluation

University of Michigan(密歇根大学)

Cristina Garbacea, Qiaozhu Mei

摘要:

基于神经网络的生成建模的最新进展重新点燃了人们对拥有能够与人类无缝对话并能够理解自然语言的计算机系统的希望。神经架构已被用于在满足各种用户需求的多种上下文和任务中以不同程度的成功生成文本摘录。值得注意的是,在大规模数据集上训练的高容量深度学习模型显示出无与伦比的学习数据模式的能力,即使在缺乏明确的监督信号的情况下,也能提供大量关于生成真实和连贯文本的新可能性。虽然自然语言生成领域正在迅速发展,但仍有许多开放的挑战需要解决。在本综述中,我们正式定义和分类的自然语言生成的问题。我们回顾特定的应用任务,这些一般配方的实例,其中生成自然语言是具有实际意义的。接下来,我们将全面概述用于生成不同文本的方法和神经架构。然而,没有标准的方法来评估这些生成模型产生的文本的质量,这构成了该领域进步的严重瓶颈。为此,我们还回顾了目前的方法来评估自然语言生成系统。我们希望这项调查将提供一个翔实的概述的配方,方法和评估神经自然语言生成。

英文摘要:

Recent advances in neural network-based generative modeling have reignited the hopes in having computer systems capable of seamlessly conversing with humans and able to understand natural language. Neural architectures have been employed to generate text excerpts to various degrees of success, in a multitude of contexts and tasks that fulfil various user needs. Notably, high capacity deep learning models trained on large scale datasets demonstrate unparalleled abilities to learn patterns in the data even in the lack of explicit supervision signals, opening up a plethora of new possibilities regarding producing realistic and coherent texts. While the field of natural language generation is evolving rapidly, there are still many open challenges to address. In this survey we formally define and categorize the problem of natural language generation. We review particular application tasks that are instantiations of these general formulations, in which generating natural language is of practical importance. Next we include a comprehensive outline of methods and neural architectures employed for generating diverse texts. Nevertheless, there is no standard way to assess the quality of text produced by these generative models, which constitutes a serious bottleneck towards the progress of the field. To this end, we also review current approaches to evaluating natural language generation systems. We hope this survey will provide an informative overview of formulations, methods, and assessments of neural natural language generation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑