NGC | Catalog
Welcome Guest


For contents of this collection and more information, please view on a desktop device.
Logo for Translation


A collection of easy to use, highly optimized Deep Learning Models for Machine Translation. Deep Learning Examples provides Data Scientist and Software Engineers with recipes to Train, fine-tune, and deploy State-of-the-Art Models




April 8, 2021
Helm Charts

Machine Translation

Machine Translation is the task of translation text from one language to another. Simply replacing one word with it's equivalent in another language rarely produces a semantically meaningful translation, because that may not account for the phrase-level meaning at all. A good machine translation system may require modeling whole sentences or phrases. Use of Neural Networks has allowed end-to-end architectures that can accomplish this, mapping from input text to the corresponding output text.A good model should be able to handle challenges like morphologically rich languages and very large vocalbularies well, while maintaining reasonable training and inference times. This Collection contains state-of-the-art models and containers that can help with the task of Machine Translation.

In this collection, we will cover:

  • Challenges in Machine Translation
  • Model architecture
  • Where to get started

Challenges in Machine Translation

Years ago, it was very time consuming to translate the text from an unknown language. Using simple vocabularies with word-for-word translation was hard for two reasons: 1) the reader had to know the grammar rules and 2) needed to keep in mind all language versions while translating the whole sentence. Now, we don’t need to struggle so much– we can translate phrases, sentences, and even large texts just by putting them in Google Translate. If the Google Translate engine tried to keep the translations for even short sentences, it wouldn’t work because of the huge number of possible variations. The best idea can be to teach the computer sets of grammar rules and translate the sentences according to them. If only it were as easy as it sounds. If you have ever tried learning a foreign language, you know that there are always a lot of exceptions to rules. When we try to capture all these rules, exceptions and exceptions to the exceptions in the program, the quality of translation breaks down.

Model architecture

i) Google’s Neural Machine Translation:

Sequence-to-Sequence (seq2seq) models are used for a variety of NLP tasks, such as text summarization, speech recognition, DNA sequence modeling, among others. Our aim is to translate given sentences from one language to another. Here, both the input and output are sentences. In other words, these sentences are a sequence of words going in and out of a model. This is the basic idea of Sequence-to-Sequence modeling. The figure below tries to explain this method.

Basic architecture

The GNMT v2 model is similar to the one discussed in Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation paper. The most important difference between the two models is in the attention mechanism. In v2 model, the output from the first LSTM layer of the decoder goes into the attention module, then the re-weighted context is concatenated with inputs to all subsequent LSTM layers in the decoder at the current time step.

Seq to Seq model

ii) Transformer based Neural Machine Translation:

The Transformer model uses standard NMT encoder-decoder architecture. This model unlike other NMT models, uses no recurrent connections and operates on fixed size context window. The encoder stack is made up of N identical layers. Each layer is composed of the following sublayers: 1. Self-attention layer 2. Feedforward network (which is 2 fully-connected layers) Like the encoder stack, the decoder stack is made up of N identical layers. Each layer is composed of the sublayers: 1. Self-attention layer 2. Multi-headed attention layer combining encoder outputs with results from the previous self-attention layer. 3. Feedforward network (2 fully-connected layers)

The encoder uses self-attention to compute a representation of the input sequence. The decoder generates the output sequence one token at a time, taking the encoder output and previous decoder-outputted tokens as inputs. The model also applies embeddings on the input and output tokens, and adds a constant positional encoding. The positional encoding adds information about the position of each token.

Transformer architecture

Where to get started

NVIDIA provides Deep Learning Examples for Image Segmentation on its GitHub repository. These examples provide you with easy to consume and highly optimized scripts for both training and inferencing. The quick start guide at our GitHub repository will help you in setting up the environment using NGC Docker Images, download pre-trained models from NGC and adapt the model training and inference for your application/use-case. Here are the examples relevant for image segmentation, directly from Deep Learning Examples:

  1. Machine translation with GNMT using PyTorch 1.1 Git repository 1.2 Uses TensorFlow 20.06-tf1-py3 NGC container

  2. Machine translation with Transformers using PyTorch 2.1 Git repository 2.2 Uses PyTorch 20.03-py3 NGC container