2010-12-01
Estimating quantitative magnitudes using semantic similarity
Publication
Publication
Presented at the
2010 AAAI Workshop (July 2010), Atlanta, GA
We present an AI called Visuo that guesses quantitative visuospatial magnitudes (e.g., heights, lengths) given adjective-noun pairs as input (e.g., "big hat"). It uses a database of tagged images as memory and infers unexperienced magnitudes by analogy with semantically-related concepts in memory. We show that transferring width-height ratios from a semantically-related concept yields significantly lower error rates than using dissimilar concepts when predicting the width-height ratios of novel inputs.
Additional Metadata | |
---|---|
2010 AAAI Workshop | |
Davies, J, & Gagné, J. (Jonathan). (2010). Estimating quantitative magnitudes using semantic similarity. In AAAI Workshop - Technical Report (pp. 14–19).
|