SQuAD is a large-scale reading comprehension dataset with 100k+ questions on Wikipedia passages, where answers are text segments, accompanied by a 51% F1 baseline model and 86.8% human performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2016 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
SQuAD: 100,000+ Questions for Machine Comprehension of Text
SQuAD is a large-scale reading comprehension dataset with 100k+ questions on Wikipedia passages, where answers are text segments, accompanied by a 51% F1 baseline model and 86.8% human performance.