Workshop on Models and Representations for Natural Human-Robot Communication (Robotics: Science and Systems)

Optimal Semantic Distance for Negative Example Selection in Grounded Language Acquisition

Nisha Pillai, Francis Ferraro, and Cynthia Matuszek

June 29, 2018

Grounded language acquisition, in which the meanings of utterances are learned from and with respect to the physical world, is often treated as a data-driven machine learning problem. For a robot, obtaining negative examples of language referents is a challenging problem: people tend to describe things that are true of a situation, rather than negatives about it.

BibTeX OWL Tweet Scholar

Downloads: 485 downloads