Machine translation is the task of translating a sentence in a source language to a different target language
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
We evaluate three simple, normalization-centric changes to improve Transformer training.
A great deal of historical corpora suffer from errors introduced by the OCR (optical character recognition) methods used in the digitization process.
Fortunately, state-of-the-art models are now being pre-trained on multiple languages (e. g. BERT was released in a multilingual version managing a hundred languages) and are exhibiting ability for zero-shot transfer from English to others languages on XNLI.
After the pre-training procedure, we use monolingual data to fine-tune the pre-trained model on downstream NLG tasks.
Generative models for text have substantially contributed to tasks like machine translation and language modeling, using maximum likelihood optimization (MLE).
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq.
Due to the unparallelizable nature of the autoregressive factorization, AutoRegressive Translation (ART) models have to generate tokens sequentially during decoding and thus suffer from high inference latency.
While most neural machine translation (NMT) systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can substantially improve final translation accuracy.