论文标题
从地图生成具有里程碑意义的导航说明作为图形到文本问题
Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem
论文作者
论文摘要
以汽车为重点的导航服务是基于命名街道的转弯和距离的，而人类自然使用的导航说明则以称为地标的物理对象为中心。我们提出了一种神经模型，该模型将OpenStreetMap表示为输入，并学会生成带有人类自然语言指令中可见且显着地标的导航说明。地图上的路由用位于自然语言指令解码的位置和旋转不变的图表表示。我们的工作基于一个新颖的数据集，该数据集是7,672个众包实例，这些数据集已通过人类导航在Street View中验证。我们的评估表明，我们系统生成的导航指令具有与人类生成的指示相似的属性，并导致街道上成功的人类导航。
Car-focused navigation services are based on turns and distances of named streets, whereas navigation instructions naturally used by humans are centered around physical objects called landmarks. We present a neural model that takes OpenStreetMap representations as input and learns to generate navigation instructions that contain visible and salient landmarks from human natural language instructions. Routes on the map are encoded in a location- and rotation-invariant graph representation that is decoded into natural language instructions. Our work is based on a novel dataset of 7,672 crowd-sourced instances that have been verified by human navigation in Street View. Our evaluation shows that the navigation instructions generated by our system have similar properties as human-generated instructions, and lead to successful human navigation in Street View.
