SOTAVerified

Leveraging Discourse Information Effectively for Authorship Attribution

2017-09-07IJCNLP 2017Code Available0· sign in to hype

Su Wang, Elisa Ferracane, Raymond J. Mooney

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We explore techniques to maximize the effectiveness of discourse information in the task of authorship attribution. We present a novel method to embed discourse features in a Convolutional Neural Network text classifier, which achieves a state-of-the-art result by a substantial margin. We empirically investigate several featurization methods to understand the conditions under which discourse features contribute non-trivial performance gains, and analyze discourse embeddings.

Tasks

Reproductions