We present the joint contribution of Unbabel and Instituto Superior Técn...
Selective rationales and counterfactual examples have emerged as two
eff...
Neural metrics for machine translation evaluation, such as COMET, exhibi...
We present the joint contribution of IST and Unbabel to the WMT 2022 Sha...
Getting the most out of limited resources allows advances in natural lan...
Modern machine learning models are opaque, and as a result there is a
bu...
A bottleneck in transformer architectures is their quadratic complexity ...
Exponential families are widely used in machine learning; they include m...
Exponential families are widely used in machine learning; they include m...
We present the contribution of the Unbabel team to the WMT 2019 Shared T...
We introduce OpenKiwi, a Pytorch-based open source framework for transla...
Word embeddings have been found to provide meaningful representations fo...