Towards End-to-End Natural Language Story Generation Systems
Towards End-to-End Natural Language Story Generation Systems
复制标题
走向端到端自然语言故事生成系统
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Santiago Ontañón
中科院分区：
文献类型：
--
作者：
Josep Valls;Jichen Zhu;Santiago Ontañón
讲故事和故事生成系统通常需要以某种形式的知识表示形式对故事世界的知识进行编码，这是一项非常耗时的任务，需要讲故事和知识工程方面的专业知识。为了缓解这一作者瓶颈，本文提出了一个端到端计算叙事系统，该系统自动从用自然语言编写的故事语料库中提取必要的领域知识，然后使用这些领域知识来生成新故事。具体来说，我们采用叙事信息提取技术，可以自动提取结构化的表示，从故事和饲料这些表示的类比为基础的故事生成系统。我们提出了我们用来连接两个现有的计算叙事系统的结构，并使用俄罗斯童话故事的数据集报告我们的实验。具体来说，我们将研究生成的最终自然语言的感知质量，以及管道中的错误如何影响输出。
Storytelling and story generation systems usually require knowledge about the story world to be encoded in some form of knowledge representation formalism, a notoriously time-consuming task requiring expertise in storytelling and knowledge engineering. In order to alleviate this authorial bottleneck, in this paper we propose an end-to-end computational narrative system that automatically extracts the necessary domain knowledge from corpus of stories written in natural language and then uses such domain knowledge to generate new stories. Specifically, we employ narrative information extraction techniques that can automatically extract structured representations from stories and feed those representations to an analogy-based story generation system. We present the structures we used to connect two existing computational narrative systems and report our experiments using a dataset of Russian fairy tales. Specifically we look at the perceived quality of the final natural language being generated and how errors in the pipeline affect the output.