Skip to Main Content
Table 1: 
Configurations for y + and y for semantic parsing. We abbreviate 𝒫(x) = 𝒦(x) : δ(y) = 1, which is the most likely output in the k-best list 𝒦(x) that leads to the correct answer, and 𝒩(x) 𝒦(x) : δ(y) = 0, which is the most likely output in the k-best list 𝒦(x) that leads to the wrong answer.
Namey +y
RAMP arg maxy∈𝒫(x) πw (y|xarg maxy∈𝒩(x) πw (y|x
RAMP1 ŷ arg maxy∈𝒩(x) πw (y|x
RAMP2 arg maxy∈𝒫(x) πw (y|xŷ 
Namey +y
RAMP arg maxy∈𝒫(x) πw (y|xarg maxy∈𝒩(x) πw (y|x
RAMP1 ŷ arg maxy∈𝒩(x) πw (y|x
RAMP2 arg maxy∈𝒫(x) πw (y|xŷ 
Close Modal

or Create an Account

Close Modal
Close Modal