constanza fierroAbout biases in the data and how that affects the factual knowledge language models learnIn this blogpost we’re going to talk about 3 papers presented at EMNLP 2021 [5,6,7] that touch on the subject of biases in the training…Jan 31, 2022Jan 31, 2022
constanza fierroinDAIR.AIRecipes for building an open-domain chatbotRecipes for building an open-domain chatbotJun 5, 2020Jun 5, 2020
constanza fierroinDAIR.AIA Light Introduction to BERTPre-training of Deep Bidirectional Transformers for Language Understanding.May 11, 2020May 11, 2020
constanza fierroinDAIR.AIAttention is all you need, the transformer architectureThis is the paper that first introduced the transformer architecture, which allowed language models to be way bigger and parallelizable.Apr 25, 2020Apr 25, 2020