Grounding of Word Meanings in Latent Dirichlet Allocation-Based Multimodal Concepts
Grounding of Word Meanings in Latent Dirichlet Allocation-Based Multimodal Concepts
复制标题
基于潜在狄利克雷分配的多模态概念中词义的基础
DOI：
10.1163/016918611x595035
复制
发表时间：
2011
影响因子：
2
通讯作者：
N. Iwahashi
中科院分区：
文献类型：
--
作者：
Tomoaki Nakamura;T. Araki;T. Nagai;N. Iwahashi
本文提出了一种基于潜在狄利克雷分配(LDA)的机器人多模式分类和词库构建框架。机器人使用其物理化身从不同的角度抓取和观察物体，并在观察期间聆听声音。这种多模式信息被用于使用多模式LDA对多模式概念进行分类和形成。同时，将观察期间获得的词汇与相关概念联系起来，由多通道LDA表示。我们还提供了一种关联性度量，用于编码单词和情态之间的联系程度。在机器人平台上实现了该算法，并进行了实验验证。我们还演示了基于学习模型的用户和机器人之间的简单对话。
In this paper we propose a latent Dirichlet allocation (LDA)-based framework for multimodal categorization and words grounding by robots. The robot uses its physical embodiment to grasp and observe an object from various view points, as well as to listen to the sound during the observing period. This multimodal information is used for categorizing and forming multimodal concepts using multimodal LDA. At the same time, the words acquired during the observing period are connected to the related concepts, which are represented by the multimodal LDA. We also provide a relevance measure that encodes the degree of connection between words and modalities. The proposed algorithm is implemented on a robot platform and some experiments are carried out to evaluate the algorithm. We also demonstrate simple conversation between a user and the robot based on the learned model.