TMLab: Generative Enhanced Model (GEM) for adversarial attacks

Autor:	Niewinski, Piotr, Pszona, Maria, Janicka, Maria
Rok vydání:	2019
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: 7 pages + appendix
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1910.00337 Zobrazit plný text záznamu View this record from Arxiv