用明喻润色写作:任务、数据集和神经方法
Writing Polishment with Simile: Task, Dataset and A Neural Approach
摘要:
比喻是一种直接进行比较的修辞手法,表示两种不同事物之间的相似之处,例如:“读论文有时会很无聊,就像看草生长一样”。人类作家经常在文本的适当位置插入适当的明喻,以使他们的作品生动活泼。然而,现有的工作都没有探索神经插值,包括定位和生成。在本文中,我们提出了一个新的任务,写作抛光与明喻(WPS),以调查是否机器能够抛光文本与明喻,我们人类做的。因此,我们设计了一个两阶段的定位和生成模型的基础上Transformer架构。我们的模型首先定位的插值应该发生的位置,然后生成一个特定位置的插值。我们还发布了一个大规模的中国明喻(CS)数据集,包含500万个明喻与上下文。实验结果证明了WPS任务的可行性,并为今后更好的自动文本润色提供了方向。
英文摘要:
A simile is a figure of speech that directly makes a comparison, showing similarities between two different things, e.g. "Reading papers can be dull sometimes,like watching grass grow". Human writers often interpolate appropriate similes into proper locations of the plain text to vivify their writings. However, none of existing work has explored neural simile interpolation, including both locating and generation. In this paper, we propose a new task of Writing Polishment with Simile (WPS) to investigate whether machines are able to polish texts with similes as we human do. Accordingly, we design a two-staged Locate&Gen model based on transformer architecture. Our model firstly locates where the simile interpolation should happen, and then generates a location-specific simile. We also release a large-scale Chinese Simile (CS) dataset containing 5 million similes with context. The experimental results demonstrate the feasibility of WPS task and shed light on the future research directions towards better automatic text polishment.
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。