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 2004.13317cs.CL
收藏

让我们变得幽默:知识增强的幽默生成

Let's be Humorous: Knowledge Enhanced Humor Generation

Sichuan University(四川大学)

Hang Zhang, Dayiheng Liu, Jiancheng Lv, Cheng Luo

摘要:

幽默的产生是一个未被充分探索和具有挑战性的问题。以前的作品主要是利用模板或替换短语来产生幽默。然而,很少有作品关注更自由的形式和幽默的背景知识。幽默的语言学理论将幽默句的结构定义为设置和笑点。在本文中,我们将探讨如何生成一个笑点给定的设置与相关知识。我们提出了一个框架,可以融合的知识,端到端的模型。据我们所知,这是第一次尝试用知识增强模型生成笑点。此外,我们创建了第一个幽默知识数据集。实验结果表明,我们的方法可以利用知识生成流畅,有趣的笑点,这优于几个基线。

英文摘要:

The generation of humor is an under-explored and challenging problem. Previous works mainly utilize templates or replace phrases to generate humor. However, few works focus on freer forms and the background knowledge of humor. The linguistic theory of humor defines the structure of a humor sentence as set-up and punchline. In this paper, we explore how to generate a punchline given the set-up with the relevant knowledge. We propose a framework that can fuse the knowledge to end-to-end models. To our knowledge, this is the first attempt to generate punchlines with knowledge enhanced model. Furthermore, we create the first humor-knowledge dataset. The experimental results demonstrate that our method can make use of knowledge to generate fluent, funny punchlines, which outperforms several baselines.

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。

↑