3-layer AWD-LSTM

Reported on 2 benchmarks across 1 task · 1 paper

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

Medical2 results

Language ModellingonPenn Treebank (Character Level)
Bit per Character (BPC)· 2018-03-22
1.175
best: 1.38 (Bipartite Flow)
An Analysis of Neural Language Modeling at Multiple Scales arXiv:1803.08240
Language ModellingonHutter Prize
Bit per Character (BPC)· 2018-03-22
1.232
best: 1.31 (RHN - depth 5 [zilly2016recurrent])
An Analysis of Neural Language Modeling at Multiple Scales arXiv:1803.08240