Story Completion with Explicit Modeling of Commonsense Knowledge
Story Completion with Explicit Modeling of Commonsense Knowledge
复制标题
DOI：
10.1109/cvprw50498.2020.00196
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Mingda Zhang;Keren Ye;R. Hwa;Adriana Kovashka
中科院分区：
文献类型：
--
作者：
Mingda Zhang;Keren Ye;R. Hwa;Adriana Kovashka
在睡前故事中长大，即使是孩子也能很容易地说出故事应该如何发展;但为故事选择一个连贯合理的结局对机器来说仍然不容易。要想成功地选择一个结尾，不仅需要对上下文进行详细的分析，还需要运用常识和基本知识。以前的工作[8]表明，在非常大的语料库上训练的语言模型可以以隐含和难以解释的方式捕获常识。我们探索了另一个方向，并提出了一种新的方法，该方法显式地结合了来自结构化数据集的常识知识[11]，并展示了改善故事完成的潜力。
Growing up with bedtime tales, even children could easily tell how a story should develop; but selecting a coherent and reasonable ending for a story is still not easy for machines. To successfully choose an ending requires not only detailed analysis of the context, but also applying commonsense reasoning and basic knowledge. Previous work [8] has shown that language models trained on very large corpora could capture common sense in an implicit and hardto-interpret way. We explore another direction and present a novel method that explicitly incorporates commonsense knowledge from a structured dataset [11], and demonstrate the potential for improving story completion.