Acquisition of grounded models of adjectival modifiers supporting semantic composition and transfer to a physical interactive robot

N. Mavridis, S. Kundig, N. Kapellas
{"title":"Acquisition of grounded models of adjectival modifiers supporting semantic composition and transfer to a physical interactive robot","authors":"N. Mavridis, S. Kundig, N. Kapellas","doi":"10.1109/ICAR.2015.7251463","DOIUrl":null,"url":null,"abstract":"Compositionality is a property of natural language which is of prime importance: It enables humans to form and conceptualize potentially novel and complex ideas, by combining words. On the other hand, the symbol grounding problem examines the way meaning is anchored to entities external to language, such as sensory percepts and sensory-motor routines. In this paper we aim towards the exploration of the intersection of compositionality and symbol grounding. We thus propose a methodology for constructing empirically derived models of grounded meaning, which afford composition of grounded semantics. We illustrate our methodology for the case of adjectival modifiers. Grounded models of adjectively modified and unmodified colors are acquired through a specially designed procedure with 134 participants, and then computational models of the modifiers “dark” and “light” are derived. The generalization ability of these learnt models is quantitatively evaluated, and their usage is demonstrated in a real-world physical humanoid robot. We regard this as an important step towards extending empirical approaches for symbol grounding so that they can accommodate compositionality: a necessary step towards the deep understanding of natural language for situated embodied agents, such as sensor-enabled ambient intelligence and interactive robots.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Advanced Robotics (ICAR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAR.2015.7251463","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Compositionality is a property of natural language which is of prime importance: It enables humans to form and conceptualize potentially novel and complex ideas, by combining words. On the other hand, the symbol grounding problem examines the way meaning is anchored to entities external to language, such as sensory percepts and sensory-motor routines. In this paper we aim towards the exploration of the intersection of compositionality and symbol grounding. We thus propose a methodology for constructing empirically derived models of grounded meaning, which afford composition of grounded semantics. We illustrate our methodology for the case of adjectival modifiers. Grounded models of adjectively modified and unmodified colors are acquired through a specially designed procedure with 134 participants, and then computational models of the modifiers “dark” and “light” are derived. The generalization ability of these learnt models is quantitatively evaluated, and their usage is demonstrated in a real-world physical humanoid robot. We regard this as an important step towards extending empirical approaches for symbol grounding so that they can accommodate compositionality: a necessary step towards the deep understanding of natural language for situated embodied agents, such as sensor-enabled ambient intelligence and interactive robots.
支持语义组合的形容词修饰语基础模型的获取和向物理交互机器人的迁移
组合性是自然语言的一种最重要的属性:它使人类能够通过组合单词来形成和概念化潜在的新颖和复杂的想法。另一方面,符号基础问题考察了意义锚定于语言外部实体的方式,如感觉知觉和感觉运动例程式化。在本文中,我们旨在探索组合性与符号基础的交集。因此,我们提出了一种构建经验推导的基础意义模型的方法,该模型提供了基础语义的组成。我们举例说明我们的方法的情况下,形容词修饰语。通过特殊设计的134人参与的程序,获得修饰色和未修饰色的接地模型,推导出修饰色“dark”和“light”的计算模型。对这些学习模型的泛化能力进行了定量评价,并在一个真实的物理类人机器人中进行了演示。我们认为这是向扩展符号基础的经验方法迈出的重要一步,这样它们就可以适应组合性:这是深入理解自然语言的必要一步,用于情境具体化代理,如启用传感器的环境智能和交互式机器人。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信