Abstract | ||
---|---|---|
In this paper we propose a trainable system that learns grounded language models from examples with a minimum of user intervention and without feedback. We have focused on the acquisition of grounded meanings of spatial and adjective/noun terms. The system has been used to understand and subsequently to generate appropriate natural language descriptions of real objects and to engage in verbal interactions with a human partner. We have also addressed the problem of resolving eventual ambiguities arising during verbal interaction through an information theoretic approach. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ROMAN.2009.5326333 | RO-MAN 2009: THE 18TH IEEE INTERNATIONAL SYMPOSIUM ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION, VOLS 1 AND 2 |
Keywords | Field | DocType |
shape,feature extraction,visualization,information theory,language model,noun,natural language,human robot interaction | Information theory,Visualization,Computer science,Noun,Feature extraction,Natural language,Artificial intelligence,Natural language processing,Adjective,Language model,Human–robot interaction | Conference |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haris Dindo | 1 | 125 | 17.49 |
Daniele Zambuto | 2 | 9 | 1.31 |