# Improving Authorship Verification using Linguistic Divergence

arXiv: https://arxiv.org/abs/2103.07052 · HTML: https://mlsanity.com/paper/2103.07052/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 12 Mar 2021.

## Builds on (most cited first, 8 of 8)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [An Army of Me: Sockpuppets in Online Discussion Communities](https://mlsanity.com/paper/1703.07355/) (2017)
- [Author Identification using Multi-headed Recurrent Neural Networks](https://mlsanity.com/paper/1506.04891/) (2015)
- [Experiments with Neural Networks for Small and Large Scale Authorship Verification](https://mlsanity.com/paper/1803.06456/) (2018)
- [Detecting Sockpuppets in Deceptive Opinion Spam](https://mlsanity.com/paper/1703.03149/) (2017)

## Abstract (arXiv)

We propose an unsupervised solution to the Authorship Verification task that utilizes pre-trained deep language models to compute a new metric called DV-Distance. The proposed metric is a measure of the difference between the two authors comparing against pre-trained language models. Our design addresses the problem of non-comparability in authorship verification, frequently encountered in small or cross-domain corpora. To the best of our knowledge, this paper is the first one to introduce a method designed with non-comparability in mind from the ground up, rather than indirectly. It is also one of the first to use Deep Language Models in this setting. The approach is intuitive, and it is easy to understand and interpret through visualization. Experiments on four datasets show our methods matching or surpassing current state-of-the-art and strong baselines in most tasks.