Modeling the difference between consecutive reasoning states, called FlowDelta, improves conversational machine comprehension accuracy across FlowQA and BERT on CoQA, QuAC, and SCONE.
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
-
FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
Modeling the difference between consecutive reasoning states, called FlowDelta, improves conversational machine comprehension accuracy across FlowQA and BERT on CoQA, QuAC, and SCONE.