BPE Dropout
Related Papers
BPE-Dropout: Simple and Effective Subword Regularization
AbstractSubword segmentation is widely used to address the open vocabulary problem in machine translation. The dominant approach to subword segmentation is Byte Pair Encoding (BPE), which keeps the most frequent …...
NRC Systems for Low Resource German-Upper Sorbian Machine Translation 2020: Transfer Learning with Lexical Modifications
AbstractWe describe the National Research Council of Canada (NRC) neural machine translation systems for the German-Upper Sorbian supervised track of the 2020 shared task on Unsupervised MT and Very Low …...
The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task
AbstractThis paper describes the submission of LMU Munich to the WMT 2020 unsupervised shared task, in two language directions, German↔Upper Sorbian. Our core unsupervised neural machine translation (UNMT) system follows …...
NRC-CNRC Systems for Upper Sorbian-German and Lower Sorbian-German Machine Translation 2021
AbstractWe describe our neural machine translation systems for the 2021 shared task on Unsupervised and Very Low Resource Supervised MT, translating between Upper Sorbian and German (low-resource) and between Lower …...
The Fujitsu DMATH Submissions for WMT21 News Translation and Biomedical Translation Tasks
AbstractThis paper describes the Fujitsu DMATH systems used for WMT 2021 News Translation and Biomedical Translation tasks. We focused on low-resource pairs, using a simple system. We conducted experiments on …...
MaxMatch-Dropout: Subword Regularization for WordPiece
AbstractWe present a subword regularization method for WordPiece, which uses a maximum matching algorithm for tokenization. The proposed method, MaxMatch-Dropout, randomly drops words in a search using the maximum matching …...