@inproceedings{mikolov2011strategies,
author = {Mikolov, Tomas and Deoras, Anoop and Povey, Daniel and Burget, Lukas and Cernocky, Jan "Honza"},
title = {Strategies for Training Large Scale Neural Network Language Models},
year = {2011},
month = {December},
abstract = {We describe how to effectively train neural network based language models on large data sets. Fast convergence during training and better overall performance is observed when the training data are sorted by their relevance. We introduce hash-based implementation of a maximum entropy model, that can be trained as a part of the neural network model. This leads to significant reduction of computational complexity. We achieved around 10% relative reduction of word error rate on English Broadcast News speech recognition task, against large 4-gram model trained on 400M tokens.},
publisher = {IEEE Automatic Speech Recognition and Understanding Workshop},
url = {http://approjects.co.za/?big=en-us/research/publication/strategies-for-training-large-scale-neural-network-language-models/},
}