Nonsense and Sensibility: Inferring Unseen Possibilities

Charles Kemp, Lauren Schmidt, Joshua B. TenenbaumeScholarship 2006

Abstract

How do we distinguish the sensible yet unlikely (blue bananas) from the nonsensical (hour-long bananas), given observations only of what is true in the world (e.g., yellow bananas)?Judgments like these may be supported by the M constraint: the assumption that ontological categories are organized into a predicability tree, and that properties apply to different subtrees within this hierarchy.We provide a computational theory that shows how the M constraint can be used to acquire predicability trees given observations only of what is true.We also suggest how the M constraint itself could be learned.
BibTeX
@inproceedings{kemp2006nonsense,
  author = {Charles Kemp and Lauren Schmidt and Joshua B. Tenenbaum},
  title = {{Nonsense and Sensibility: Inferring Unseen Possibilities}},
  booktitle = {eScholarship},
  year = {2006},
}

Loading related content...

Figure