CABINET: Content Relevance based Noise Reduction for Table Question Answering
Open paper
Other version
Benchmark
Model
Rank
Results
semantic-parsing-on-wikisql
CABINET
#3
Denotation accuracy (test): 89.5
semantic-parsing-on-wikitablequestions
CABINET
#6
Accuracy (Test): 69.1
Accuracy (Dev): /
table-to-text-generation-on-fetaqa
CABINET
#1
BLEU: 40.5
Rank counts only results with a code link.