WriterForcing:生成更有趣的故事结局
WriterForcing: Generating more interesting story endings
摘要:
我们研究的问题产生有趣的故事结局。神经生成模型已经在各种文本生成问题上显示出了很好的结果。序列到序列(Seq2Seq)模型通常被训练为针对给定的输入序列生成单个输出序列。然而,在一个故事的背景下,多个结局是可能的。Seq2Seq模型倾向于忽略上下文并生成通用和乏味的响应。很少有作品研究在给定的故事背景下产生多样化和有趣的故事结局。在本文中,我们提出了通过以下方式生成更多样化和有趣的输出的模型:1)训练模型以将注意力集中在故事的重要关键词上,以及2)促进非通用词的生成。我们表明,两者的结合导致更多样化和有趣的结局。
英文摘要:
We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single output sequence for a given input sequence. However, in the context of a story, multiple endings are possible. Seq2Seq models tend to ignore the context and generate generic and dull responses. Very few works have studied generating diverse and interesting story endings for a given story context. In this paper, we propose models which generate more diverse and interesting outputs by 1) training models to focus attention on important keyphrases of the story, and 2) promoting generation of non-generic words. We show that the combination of the two leads to more diverse and interesting endings.
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。