论文标题
用比喻：任务，数据集和神经方法写作
Writing Polishment with Simile: Task, Dataset and A Neural Approach
论文作者
论文摘要
明喻是直接进行比较的语音数字，显示了两种不同的事物之间的相似之处，例如“阅读论文有时可能会很乏味，就像看草的生长一样”。人类作家经常将适当的比喻插入纯文本的适当位置，以生动其著作。但是，现有的工作都没有探索神经明敏插值，包括定位和发电。在本文中，我们提出了一项新的任务，即用Simile（WPS）编写餐具，以调查机器是否能够像人类一样用比喻来抛光文本。因此，我们设计了一个基于变压器体系结构的两级定位和加登模型。我们的模型首先定位静物插值应发生的位置，然后生成特定于位置的明喻。我们还发布了一个大型中国明喻（CS）数据集，该数据集包含500万个具有上下文的比喻。实验结果证明了WPS任务的可行性，并阐明了未来的研究方向，以更好的自动文本餐饮。
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.
