Title :
Co-learning nouns and adjectives
Author :
Orhan, Guner ; Olgunsoylu, Sertac ; Sahin, Erol ; kalkan, Sinan
Author_Institution :
KOVAN Res. Lab., Middle East Tech. Univ., Ankara, Turkey
Abstract :
In cognitive robotics community, categories belonging to adjectives and nouns have been learned separately and independently. In this article, we propose a prototype-based framework that conceptualize adjectives and nouns as separate categories that are, however, linked to and interact with each other. We demonstrate how this co-learned concepts might be useful for a cognitive robot, especially using a game called “What object is it?” that involves finding an object based on a set of adjectives.
Keywords :
cognitive systems; learning (artificial intelligence); natural language processing; robots; adjective learning; co-learned concepts; cognitive robotics community; noun learning; prototype-based framework; Accuracy; Feature extraction; Noise measurement; Prototypes; Robot sensing systems; Visualization;
Conference_Titel :
Development and Learning and Epigenetic Robotics (ICDL), 2013 IEEE Third Joint International Conference on
Conference_Location :
Osaka
DOI :
10.1109/DevLrn.2013.6652550