4 papers
Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
Gonçalo M. Correia, Vlad Niculae, Wilker Aziz +1
Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or comb…
Adaptively Sparse Transformers
Gonçalo M. Correia, Vlad Niculae, André F. T. Martins
Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed a…
Unbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing
António V. Lopes, M. Amin Farajian, Gonçalo M. Correia +2
This paper describes Unbabel's submission to the WMT2019 APE Shared Task for the English-German language pair. Following the recent rise of large, powerful, pre-trained models, we…
A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning
Gonçalo M. Correia, André F. T. Martins
Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits. APE systems are usually trained by co…