arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.00337cs.CLcs.LG
收藏

TMLab:用于对抗攻击的生成增强模型(GEM)

TMLab: Generative Enhanced Model (GEM) for adversarial attacks

Samsung R&D Institute Poland(三星波兰研发研究所)

Piotr Niewinski, Maria Pszona, Maria Janicka

摘要:

我们提出了我们的生成增强模型(GEM),我们用来创建在FEVER 2.0断路器任务中获得一等奖的样本。GEM是在GPT-2体系结构基础上发展起来的扩展语言模型。将新的目标词汇输入添加到已经存在的上下文输入使得能够进行受控文本生成。训练过程导致创建了一个模型,该模型继承了预训练的GPT-2的知识,因此可以在任务域中生成类似自然的英语句子,并进行一些额外的控制。因此,GEM产生了恶意的说法,混淆了各种文章的事实,因此很难对其真实性进行分类。

英文摘要:

We present our Generative Enhanced Model (GEM) that we used to create samples awarded the first prize on the FEVER 2.0 Breakers Task. GEM is the extended language model developed upon GPT-2 architecture. The addition of novel target vocabulary input to the already existing context input enabled controlled text generation. The training procedure resulted in creating a model that inherited the knowledge of pretrained GPT-2, and therefore was ready to generate natural-like English sentences in the task domain with some additional control. As a result, GEM generated malicious claims that mixed facts from various articles, so it became difficult to classify their truthfulness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑