pith. sign in

arxiv: 1709.02271 · v1 · pith:O56RUFISnew · submitted 2017-09-07 · 💻 cs.CL

Leveraging Discourse Information Effectively for Authorship Attribution

classification 💻 cs.CL
keywords discourseattributionauthorshipfeaturesinformationachievesanalyzeclassifier
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.