A generate-validate QA method that scores template-generated English hypotheses with BERT/ESIM textual entailment reaches 76.63% on QUAREL, beating QUASP+ by 7.93 points.
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
-
A Generate-Validate Approach to Answering Questions about Qualitative Relationships
A generate-validate QA method that scores template-generated English hypotheses with BERT/ESIM textual entailment reaches 76.63% on QUAREL, beating QUASP+ by 7.93 points.