Two neural agents can play a log(4)-questions sentence-guessing game with about 80 percent accuracy, but question meaningfulness and game accuracy are in tension.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Playing log(N)-Questions over Sentences
Two neural agents can play a log(4)-questions sentence-guessing game with about 80 percent accuracy, but question meaningfulness and game accuracy are in tension.