Feature Vector Difference based Authorship Verification for Open-World Settings

Feature Vector Difference based Authorship Verification for Open-World Settings
复制标题

开放世界设置中基于特征向量差异的作者身份验证

DOI:
--
复制
发表时间:
2021
期刊:
--
影响因子:
--
通讯作者:
Rachel Greenstadt
Rachel Greenstadt
中科院分区:
--
文献类型:
--
作者:
Janith Weerasinghe;Rhia Singh;Rachel Greenstadt

文献摘要

参考文献

被引文献

相似文献

本文描述了我们为PAN 2021作者身份验证任务创建机器学习模型的方法。此任务的目标是预测给定的文档对是否由同一作者编写。对于每个文档对,我们从文档中提取风格特征,并使用特征向量之间的绝对差异作为分类器的输入。我们的新模型与去年的模型相似,只是对特征集和分类器进行了轻微的改进。我们在两个小数据集和两个大数据集上训练了两个模型,它们的auc都达到了0。967和0。972在最后的评估。
This paper describes the approach we took to create a machine learning model for the PAN 2021 Au-thorship Verification Task. The goal of this task is to predict if a given pair of documents are written by the same author. For each document pair, we extracted stylometric features from the documents and used the absolute difference between the feature vectors as input to our classifier. Our new model is similar to out last year’s model with minor improvements to the feature set and the classifier. We trained two models on the two small and large datasets which achieved AUCs of 0 . 967 and 0 . 972 in the final evaluations.
DOI: --
发表时间: 2020
期刊: --
影响因子: --
作者:
Janith Weerasinghe;R. Greenstadt
通讯作者: Janith Weerasinghe;R. Greenstadt