arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1805.07952cs.CL
收藏

一个新的数据集和模型,用于学习理解导航指令

A new dataset and model for learning to understand navigational instructions

Koç University(科奇大学)

Ozan Arkan Can, Deniz Yuret

摘要:

在本文中,我们提出了一个最先进的模型,并介绍了一个新的数据集用于接地语言学习。我们的目标是开发一个模型,可以学习遵循新的指令给定先前的预防-感知-行动的例子。我们的工作基于SAIL数据集,该数据集由迷宫般的环境中的导航指令和动作组成。我们提出的新模型通过使用可以表示对象相对位置的改进的感知组件,在SAIL数据集上实现了迄今为止的最佳结果。我们还分析了SAIL数据集在大小和平衡方面的问题。我们认为,在一个小的,固定大小的数据集上的性能不再是区分最先进模型的好方法。我们介绍了SAILx,一个合成数据集生成器,并进行实验,控制数据集的大小和平衡。

英文摘要:

In this paper, we present a state-of-the-art model and introduce a new dataset for grounded language learning. Our goal is to develop a model that can learn to follow new instructions given prior instruction-perception-action examples. We based our work on the SAIL dataset which consists of navigational instructions and actions in a maze-like environment. The new model we propose achieves the best results to date on the SAIL dataset by using an improved perceptual component that can represent relative positions of objects. We also analyze the problems with the SAIL dataset regarding its size and balance. We argue that performance on a small, fixed-size dataset is no longer a good measure to differentiate state-of-the-art models. We introduce SAILx, a synthetic dataset generator, and perform experiments where the size and balance of the dataset are controlled.

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。

↑