Spatial Referring Expression Generation for HRI: Algorithms and Evaluation Framework

Spatial Referring Expression Generation for HRI: Algorithms and Evaluation Framework
复制标题

HRI 的空间指代表达式生成:算法和评估框架

DOI:
10.3115/1708322.1708333
复制
发表时间:
2017
期刊:
Linguistic Issues in Language Technology
影响因子:
--
通讯作者:
Matthias Scheutz
Matthias Scheutz
中科院分区:
--
文献类型:
--
作者:
Lars Kunze;T. Williams;Nick Hawes;Matthias Scheutz

文献摘要

参考文献

被引文献

相似文献

引用对象、位置和人等实体的能力是设计用于与人类交互的机器人的重要能力。例如,诸如“你是说左边的那个盒子吗?”之类的指称表达(RE)。可能被机器人用来消除物体之间的歧义。在本文中,我们提出并评估算法的引用表达式生成(REG)在小规模的情况下。我们首先介绍了人类如何产生小规模空间指涉表达(RE)的数据。然后,我们使用这些数据来定义观察到的小规模空间RE的五个类别,并使用这些类别来创建REG算法的集合。接下来,我们通过一组相互关联的众包实验,主观地(通过让参与者对RE进行排名)和客观地(通过评估参与者使用RE时的任务性能)评估这些算法和人类生成的RE。虽然我们的机器生成的RE在主观上低于人类生成的RE,但它们在客观上显著优于人类RE。最后,我们讨论了这项工作的主要贡献:(1)图像和RE的数据集,(2)观察到的小规模空间RE的分类,(3)REG算法的集成,以及(4)基于众包的框架,用于主观和客观地评估REG。
The ability to refer to entities such as objects, locations, and people is an important capability for robots designed to interact with humans. For example, a referring expression (RE) such as “Do you mean the box on the left?” might be used by a robot seeking to disambiguate between objects. In this paper, we present and evaluate algorithms for Referring Expression Generation (REG) in small-scale situated contexts. We first present data regarding how humans generate small-scale spatial referring expressions (REs). We then use this data to define five categories of observed small-scale spatial REs, and use these categories to create an ensemble of REG algorithms. Next, we evaluate REs generated by those algorithms and by humans both subjectively (by having participants rank REs), and objectively, (by assessing task performance when participants use REs) through a set of interrelated crowdsourced experiments. While our machine generated REs were subjectively rated lower than those generated by humans, they objectively significantly outperformed human REs. Finally, we discuss the main contributions of this work: (1) a dataset of images and REs, (2) a categorization of observed small-scale spatial REs, (3) an ensemble of REG algorithms, and (4) a crowdsourcing-based framework for sub-jectively and objectively evaluating REG.
DOI: 10.1109/iros.2014.6942963
发表时间: 2014-09
期刊: --
影响因子: --
作者:
Lars Kunze;Christopher Burbridge;Marina Alberti;Akshaya Thippur;J. Folkesson;P. Jensfelt;Nick Hawes
通讯作者: Lars Kunze;Christopher Burbridge;Marina Alberti;Akshaya Thippur;J. Folkesson;P. Jensfelt;Nick Hawes
DOI: --
发表时间: 2008
期刊: --
影响因子: --
作者:
A Belz
通讯作者: A Belz
2009 年 TUNA-REG 挑战赛:概述和评估结果
DOI: --
发表时间: 2009
期刊: --
影响因子: --
作者:
A Gatt
通讯作者: A Gatt
用于主动视觉对象搜索的定性空间关系的引导概率模型
DOI: --
发表时间: 2014
期刊: --
影响因子: --
作者:
Kunze L
通讯作者: Kunze L