Can I read Author Identification using Multi-headed Recurrent Neural Networks on EtoBox?

Author Identification using Multi-headed Recurrent Neural Networks by Bagnall, Douglas is a scholarly article available to read on EtoBox.

What is Author Identification using Multi-headed Recurrent Neural Networks about?

Recurrent neural networks (RNNs) are very good at modelling the flow of text, but typically need to be trained on a far larger corpus than is available for the PAN 2015 Author Identification task. This paper describes a novel approach where the output layer of a character-level RNN language model is split into several independent predictive sub-models, each representing an author, while the recurrent layer is shared by all. This allows the recurrent layer to model the language as a whole without over-fitting, while the outputs select aspects of the underlying model that reflect their author's style. The method proves competitive, ranking first in two of the four languages.

Author

Bagnall, Douglas

Published

2015

Language

EN