Improving Authorship Verification using Linguistic Divergence
This work addresses authorship verification for forensic or literary analysis, but it is incremental as it builds on existing deep language model approaches with a novel metric.
The authors tackled authorship verification by proposing an unsupervised method using pre-trained deep language models to compute a new metric called DV-Distance, which addresses non-comparability issues in small or cross-domain corpora. Experiments on four datasets showed their method matching or surpassing current state-of-the-art and strong baselines in most tasks.
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.