arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.01109cs.CL
收藏

构建故事生成的策略

Strategies for Structuring Story Generation

FAIR(FAIR(脸书人工智能研究院));LORIA(洛林信息学及其应用研究实验室);Google AI(谷歌人工智能)

Angela Fan, Mike Lewis, Yann Dauphin

摘要:

作家一般依靠计划或草图来写长篇故事,但大多数当前的语言模型都是从左到右一个字一个字地生成。我们探索了由粗到细的模型,用于创建数百个单词的叙事文本,并引入了通过抽象动作和实体来分解故事的新模型。该模型首先生成文本的谓词-论元结构,其中对同一实体的不同提及用占位符标记。然后生成谓词-参数结构的表面实现,最后用上下文相关的名称和引用替换实体占位符。人类法官更喜欢我们模型中的故事,而不是以前的各种分层文本生成方法。广泛的分析表明,我们的方法可以帮助提高生成的故事中的事件和实体的多样性和一致性。

英文摘要:

Writers generally rely on plans or sketches to write long stories, but most current language models generate word by word from left to right. We explore coarse-to-fine models for creating narrative texts of several hundred words, and introduce new models which decompose stories by abstracting over actions and entities. The model first generates the predicate-argument structure of the text, where different mentions of the same entity are marked with placeholder tokens. It then generates a surface realization of the predicate-argument structure, and finally replaces the entity placeholders with context-sensitive names and references. Human judges prefer the stories from our models to a wide range of previous approaches to hierarchical text generation. Extensive analysis shows that our methods can help improve the diversity and coherence of events and entities in generated stories.

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。

↑