1 |
Neuronale maschinelle Übersetzung für ressourcenarme Szenarien ... : Neural machine translation for low-resource scenarios ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
When and Why is Unsupervised Neural Machine Translation Useless? ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Generalizing Back-Translation in Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Learning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages ...
|
|
|
|
Abstract:
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We propose three methods to increase the relation among source, pivot, and target languages in the pre-training: 1) step-wise training of a single model for different language pairs, 2) additional adapter component to smoothly connect pre-trained encoder and decoder, and 3) cross-lingual encoder training via autoencoding of the pivot language. Our methods greatly outperform multilingual models up to +2.6% BLEU in WMT 2019 French-German and German-Czech tasks. We show that our improvements are valid also in zero-shot/zero-resource scenarios. ... : EMNLP 2019 camera-ready ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1909.09524 https://arxiv.org/abs/1909.09524
|
|
BASE
|
|
Hide details
|
|
7 |
Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018 ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018 ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|