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|
In this work, we introduce unsupervised pivot translation for distant languages, which translates a language to a distant language through multiple hops, and the unsupervised translation on each hop is relatively easier than the original direct translation.
Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words.
Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input.
Non-autoregressive translation models (NAT) have achieved impressive inference speedup.
Contrary to popular belief, Optical Character Recognition (OCR) remains a challenging problem when text occurs in unconstrained environments, like natural scenes, due to geometrical distortions, complex backgrounds, and diverse fonts.
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data.
Transformer is the state-of-the-art model in recent machine translation evaluations.
During training, one can feed KERMIT paired data $(x, y)$ to learn the joint distribution $p(x, y)$, and optionally mix in unpaired data $x$ or $y$ to refine the marginals $p(x)$ or $p(y)$.
To integrate different segmentations with the state-of-the-art NMT model, Transformer, we propose lattice-based encoders to explore effective word or subword representation in an automatic way during training.
In this work, we present novel approaches to exploit sentential context for neural machine translation (NMT).