Recently, there has been a rise in the development of powerful pre-trained
natural language models, including GPT-2, Grover, and XLM. These models have
shown state-of-the-art capabilities towards a variety of different NLP tasks,
including question answering, content summarisation, and text generation.
Alongside this, there have been many studies focused on online authorship
attribution (AA). That is, the use of models to identify the authors of online
texts. Given the power of natural language models in generating convincing
texts, this paper examines the degree to which these language models can
generate texts capable of deceiving online AA models. Experimenting with both
blog and Twitter data, we utilise GPT-2 language models to generate texts using
the existing posts of online users. We then examine whether these AI-based text
generators are capable of mimicking authorial style to such a degree that they
can deceive typical AA models. From this, we find that current AI-based text
generators are able to successfully mimic authorship, showing capabilities
towards this on both datasets. Our findings, in turn, highlight the current
capacity of powerful natural language models to generate original online posts
capable of mimicking authorial style sufficiently to deceive popular AA
methods; a key finding given the proposed role of AA in real world applications
such as spam-detection and forensic investigation.

本文探讨自然语言模型在生成具有被误认为是他人所写的能力的在线文本方面的潜力，发现当前的这类技术中 GPT-2 可成功地模拟与欺骗常见的作者识别的方法，说明了这类技术的巨大潜力和其实际应用如非法信息识别和犯罪取证的重要性。

使用神经文本生成器欺骗在线作者归属模型：你是罗伯特还是罗伯塔？

Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators

We present an overview of the EmotionGIF2020 Challenge, held at the 8th
International Workshop on Natural Language Processing for Social Media
(SocialNLP), in conjunction with ACL 2020. The challenge required predicting
affective reactions to online texts, and included the EmotionGIF dataset, with
tweets labeled for the reaction categories. The novel dataset included 40K
tweets with their reaction GIFs. Due to the special circumstances of year 2020,
two rounds of the competition were conducted. A total of 84 teams registered
for the task. Of these, 25 teams success-fully submitted entries to the
evaluation phase in the first round, while 13 teams participated successfully
in the second round. Of the top participants, five teams presented a technical
report and shared their code. The top score of the winning team using the
Recall@K metric was 62.47%.

该论文主要介绍了 2020 年 ACL 会议上举办的 EmotionGIF2020 比赛及其数据集（包含 40,000 条带有反应表情的推文），旨在预测用户对于在线文本的情感反应，并评估了参赛队伍的表现，获胜队伍再 Recall@K 指标下的得分为 62.47%。