Melis et al. (2017) - 1-layer LSTM (tied)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Medical2 results

Language ModellingonWikiText-2
Test perplexity· 2017-07-18
65.9
best: 8.21 (SparseGPT (175B, 50% Sparsity))
SOTA
On the State of the Art of Evaluation in Neural Language Models arXiv:1707.05589
Language ModellingonWikiText-2
Validation perplexity· 2017-07-18
69.3
best: 15.69 (GPT-2 (fine-tuned))
SOTA
On the State of the Art of Evaluation in Neural Language Models arXiv:1707.05589