Enhancing Unsupervised Natural Language Grounding through Explicit Teaching
Title: Enhancing Unsupervised Natural Language Grounding through Explicit Teaching
Authors: Oliver Roesler (Artificial Intelligence Lab, Vrije Universiteit Brussel);
Year: 2020
Citation: Roesler, O., (2020). Enhancing Unsupervised Natural Language Grounding through Explicit Teaching. UKRAS20 Conference: “Robots into the real world” Proceedings, 3-5. doi: 10.31256/Bf9Vw8C
Abstract:
In this paper, a grounding framework is proposed that combines unsupervised and supervised grounding by extend- ing an unsupervised grounding model with a mechanism to learn from explicit human teaching. To investigate whether explicit teaching improves the sample efficiency of the original model, both models are evaluated through an interaction experiment between a human tutor and a robot in which synonymous shape, color, and action words are grounded through geometric object characteristics, color histograms, and kinematic joint features. The results show that explicit teaching improves the sample efficiency of the unsupervised baseline model.