Authorship clustering using multi-headed recurrent neural networks
Computation and Language
2016-08-17 v1
Abstract
A recurrent neural network that has been trained to separately model the language of several documents by unknown authors is used to measure similarity between the documents. It is able to find clues of common authorship even when the documents are very short and about disparate topics. While it is easy to make statistically significant predictions regarding authorship, it is difficult to group documents into definite clusters with high accuracy.
Cite
@article{arxiv.1608.04485,
title = {Authorship clustering using multi-headed recurrent neural networks},
author = {Douglas Bagnall},
journal= {arXiv preprint arXiv:1608.04485},
year = {2016}
}
Comments
14 pages, 5 figures; notebook for PAN@CLEF 2016