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.

本篇论文提出了 Writing Polishment with Simile（WPS）的新任务，探究机器是否能够像我们人类一样，使用比喻精细地改善文本。在此基础上，使用 transformer 架构设计两阶段 Locate&Gen 模型，首先定位比喻插值应该出现的位置，然后生成与该位置相关的比喻，实验结果证明了 WPS 任务的可行性，并揭示了未来研究方向，以 实现更好的自动文本精修。同时，文章释出了一个包含 500 万个带上下文中文比喻的数据集。

使用比喻进行写作润色：任务、数据集和神经网络方法