1k citations · 10.8k across the 111 of their papers we have counts for
3 papers · 2 filters
Language Models are Open Knowledge Graphs
Chenguang Wang, Xiao Liu, Dawn Song
This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are bu…
Pretrained Transformers Improve Out-of-Distribution Robustness
Dan Hendrycks, Xiaoyuan Liu, Eric Wallace +3
Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribut…
Imitation Attacks and Defenses for Black-box Machine Translation Systems
Eric Wallace, Mitchell Stern, Dawn Song
Adversaries may look to steal or attack black-box NLP systems, either for financial gain or to exploit model errors. One setting of particular interest is machine translation (MT),…