A model that learns when to draw answer words from a knowledge base instead of the passage can generate higher-quality answers on the MS MARCO benchmark.
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
-
Incorporating External Knowledge into Machine Reading for Generative Question Answering
A model that learns when to draw answer words from a knowledge base instead of the passage can generate higher-quality answers on the MS MARCO benchmark.