bAbI QA #1 bAbI QA #2 bAbI QA #3 bAbI QA #4 RaSoR 100.0 60.0 71.0 81.0 BiDAF 100.0 42.0 53.0 83.0 DocumentReader 100.0 63.0 70.0 100.0 DocumentReader (no external features) 100.0 76.0 93.0 100.0 BiDAF++ 100.0 100.0 100.0 78.0 MnemonicReader 100.0 44.0 71.0 100.0 MnemonicReader (no ...
bAbI QA #1 bAbI QA #2 bAbI QA #3 bAbI QA #4 RaSoR 100.0 60.0 71.0 81.0 BiDAF 100.0 42.0 53.0 83.0 DocumentReader 100.0 63.0 70.0 100.0 DocumentReader (no external features) 100.0 76.0 93.0 ...
The number of hidden layers, the number of units in each layer, regularization techniques, network weight initialization, activation functions, learning rate, momentum values, number of ...
My previous post on summarising 57 research papers turned out to be quite useful for people working in this field, so it is about time…
Researchers from Facebook are presenting a wide range of research at the 2019 meeting of the Association for Computational Linguistics (ACL).