“Scruffy Reasoning — I work in an imprecise world: I start with structured knowledge representations and classic algorithms, and then I generalize them to be more compatible with the incomplete and noisy data of the real world.”
More from Catherine Havasi
“Normalization inherently involves discarding information, but since ConceptNet 3, we have…”
“ConceptNet includes not just definitions and lexical relationships, but also the…”
“Each sentence of OMCS was entered by a goal-directed user hoping to contribute common…”