Author Identification using Multi-headed Recurrent Neural Networks
Abstract
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.
Cite
@article{arxiv.1506.04891,
title = {Author Identification using Multi-headed Recurrent Neural Networks},
author = {Douglas Bagnall},
journal= {arXiv preprint arXiv:1506.04891},
year = {2016}
}
Comments
8 pages, 3 figures Version 1 was a notebook for the PAN@CLEF Author Identification challenge. Version 2 is expanded to be a full paper for CLEF2016