NMT
490 papers with code • 0 benchmarks • 0 datasets
Neural machine translation is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.
Benchmarks
These leaderboards are used to track progress in NMT
Libraries
Use these libraries to find NMT models and implementationsMost implemented papers
Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models
yurayli/stanford-cs224n-sol
•
•
ACL 2016
We build hybrid systems that translate mostly at the word level and consult the character components for rare words.
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
ZhenYangIACAS/NMT_GAN
•
•
NAACL 2018
During training, both the dynamic discriminator and the static BLEU objective are employed to evaluate the generated sentences and feedback the evaluations to guide the learning of the generator.
Synthetic and Natural Noise Both Break Neural Machine Translation
Character-based neural machine translation (NMT) models alleviate out-of-vocabulary issues, learn morphology, and move us closer to completely end-to-end translation systems.
On Adversarial Examples for Character-Level Neural Machine Translation
Evaluating on adversarial examples has become a standard procedure to measure robustness of deep learning models.
SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing
google/sentencepiece
•
•
EMNLP 2018
We perform a validation experiment of NMT on English-Japanese machine translation, and find that it is possible to achieve comparable accuracy to direct subword training from raw sentences.
Unsupervised Statistical Machine Translation
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018).
CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB
facebookresearch/LASER
•
•
ACL 2021
To evaluate the quality of the mined bitexts, we train NMT systems for most of the language pairs and evaluate them on TED, WMT and WAT test sets.
Incorporating BERT into Neural Machine Translation
bert-nmt/bert-nmt
•
•
ICLR 2020
While BERT is more commonly used as fine-tuning instead of contextual embedding for downstream language understanding tasks, in NMT, our preliminary exploration of using BERT as contextual embedding is better than using for fine-tuning.
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings
masoudjs/simalign
•
•
Findings of the Association for Computational Linguistics 2020
We find that alignments created from embeddings are superior for four and comparable for two language pairs compared to those produced by traditional statistical aligners, even with abundant parallel data; e. g., contextualized embeddings achieve a word alignment F1 for English-German that is 5 percentage points higher than eflomal, a high-quality statistical aligner, trained on 100k parallel sentences.
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations.
