Ненаблюдаемая нейронная машинная перевод
Related Papers
Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation
AbstractUnsupervised bilingual word embedding (UBWE), together with other technologies such as back-translation and denoising, has helped unsupervised neural machine translation (UNMT) achieve remarkable results in several language pairs. In previous …...
Filtering Back-Translated Data in Unsupervised Neural Machine Translation
AbstractUnsupervised neural machine translation (NMT) utilizes only monolingual data for training. The quality of back-translated data plays an important role in the performance of NMT systems. In back-translation, all generated …...
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
AbstractUnsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for …...
Reference Language based Unsupervised Neural Machine Translation
AbstractExploiting a common language as an auxiliary for better translation has a long tradition in machine translation and lets supervised learning-based machine translation enjoy the enhancement delivered by the well-used …...
Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT
AbstractUsing a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results. When limited data …...
Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training
AbstractUnsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community. The main advantage of the UNMT lies in its easy collection of required large training …...
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 …...
Crosslingual Embeddings are Essential in UNMT for distant languages: An English to IndoAryan Case Study
AbstractRecent advances in Unsupervised Neural Machine Translation (UNMT) has minimized the gap between supervised and unsupervised machine translation performance for closely related language-pairs. However and the situation is very different …...
Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation
AbstractSuccessful methods for unsupervised neural machine translation (UNMT) employ cross-lingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the …...
Scrambled Translation Problem: A Problem of Denoising UNMT
AbstractIn this paper and we identify an interesting kind of error in the output of Unsupervised Neural Machine Translation (UNMT) systems like Undreamt1. We refer to this error type as …...
Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation
AbstractBack-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is trained on the pseudo parallel data …...
Vocabulary-informed Language Encoding
AbstractA Multilingual model relies on language encodings to identify input languages because the multilingual model has to distinguish between the input and output languages or among all the languages for …...
On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss
AbstractAlthough unsupervised neural machine translation (UNMT) has achieved success in many language pairs, the copying problem, i.e., directly copying some parts of the input sentence as the translation, is common …...