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 1801.05096cs.ROcs.CLcs.HC
收藏

基于GAN分类的操作指令的基础语言理解

Grounded Language Understanding for Manipulation Instructions Using GAN-Based Classification

National Institute of Information and Communications Technology(国立信息与通信技术研究所)

Komei Sugiura, Hisashi Kawai

摘要:

本研究的目标任务是国内服务机器人(DSRs)接地语言理解。特别是,我们专注于指导理解的动词缺失的短句。这一任务对于构建通信的DSRs至关重要,因为操纵对于DSRs是必不可少的。现有的指令理解方法通常只从非基础知识中估计缺失的信息,因此,预测的动作是否是物理上可执行的还不清楚。在本文中,我们提出了一个接地的指令理解方法来估计适当的对象给定的指令和情况。我们扩展了生成对抗网络(GAN),并使用潜在表示构建了一个基于GAN的分类器。为了定量评估所提出的方法,我们已经开发了一个数据集的基础上,用于视觉QA的标准数据集。实验结果表明,该方法比基线方法得到更好的结果。

英文摘要:

The target task of this study is grounded language understanding for domestic service robots (DSRs). In particular, we focus on instruction understanding for short sentences where verbs are missing. This task is of critical importance to build communicative DSRs because manipulation is essential for DSRs. Existing instruction understanding methods usually estimate missing information only from non-grounded knowledge; therefore, whether the predicted action is physically executable or not was unclear. In this paper, we present a grounded instruction understanding method to estimate appropriate objects given an instruction and situation. We extend the Generative Adversarial Nets (GAN) and build a GAN-based classifier using latent representations. To quantitatively evaluate the proposed method, we have developed a data set based on the standard data set used for Visual QA. Experimental results have shown that the proposed method gives the better result than baseline methods.

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。

↑