Bi-Attention + DCU-LSTM

Reported on 4 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Question AnsweringonSearchQA
N-gram F1
59.5
best: 70.8 (DecaProp)
Question AnsweringonSearchQA
Unigram Acc
49.4
best: 62.2 (DecaProp)
Open-Domain Question AnsweringonSearchQA
N-gram F1
59.5
best: 70.8 (DecaProp)
Open-Domain Question AnsweringonSearchQA
Unigram Acc
49.4
best: 62.2 (DecaProp)