Online Representation Learning in Recurrent Neural Language Models
Computation and Language
2017-03-07 v1 Machine Learning
Neural and Evolutionary Computing
Abstract
We investigate an extension of continuous online learning in recurrent neural network language models. The model keeps a separate vector representation of the current unit of text being processed and adaptively adjusts it after each prediction. The initial experiments give promising results, indicating that the method is able to increase language modelling accuracy, while also decreasing the parameters needed to store the model along with the computation required at each step.
Cite
@article{arxiv.1508.03854,
title = {Online Representation Learning in Recurrent Neural Language Models},
author = {Marek Rei},
journal= {arXiv preprint arXiv:1508.03854},
year = {2017}
}
Comments
In Proceedings of EMNLP 2015