Adaptive Softmax is a speedup technique for the computation of probability distributions over words. The adaptive softmax is inspired by the class-based hierarchical softmax, where the word classes are built to minimize the computation time. Adaptive softmax achieves efficiency by explicitly taking into account the computation time of matrix-multiplication on parallel systems and combining it with a few important observations, namely keeping a shortlist of frequent words in the root node and reducing the capacity of rare words.
Source: Efficient softmax approximation for GPUsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Language Modelling | 36 | 40.91% |
Machine Translation | 7 | 7.95% |
Speech Recognition | 5 | 5.68% |
Text Generation | 3 | 3.41% |
Automatic Speech Recognition | 3 | 3.41% |
Abstractive Text Summarization | 2 | 2.27% |
Paraphrase Identification | 2 | 2.27% |
Question Answering | 2 | 2.27% |
Sentiment Analysis | 2 | 2.27% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |