Search Results for author: António V. Lopes

Found 4 papers, 1 papers with code

One Wide Feedforward is All You Need

no code implementations4 Sep 2023 Telmo Pessoa Pires, António V. Lopes, Yannick Assogba, Hendra Setiawan

The Transformer architecture has two main non-embedding components: Attention and the Feed Forward Network (FFN).

Decoder Position

Unbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing

no code implementations WS 2019 António V. Lopes, M. Amin Farajian, Gonçalo M. Correia, Jonay Trenous, André F. T. Martins

Analogously to dual-encoder architectures we develop a BERT-based encoder-decoder (BED) model in which a single pretrained BERT encoder receives both the source src and machine translation tgt strings.

Automatic Post-Editing Decoder +2

Cannot find the paper you are looking for? You can Submit a new open access paper.