From the course: Introduction to Attention-Based Neural Networks
Join today to access over 24,600 courses taught by industry experts.
Sequence to sequence models for language translation
From the course: Introduction to Attention-Based Neural Networks
Sequence to sequence models for language translation
- Now that we have a big picture idea of how language generation models work, let's understand how language translation models work. These are sequence to sequence models. Let's assume we have a simple language translation model to translate from English to German. So if you feed an I ate an apple you'll get the equivalent sentence in German. Please forgive me if I don't try to pronounce the German sentence. I'll just fail miserably. Now, language translation models are sequence to sequence models, and the model structure uses two different networks. The first network is an encoder, and the second network is a decoder. Because the encoder takes in the sentence in the original language as an input, The encoder is an RNN. The decoder produces a sentence in the target language as an output. The decoder is also an RNN. The encoder works on the sequential input in the source language. Decoder produces sequential output…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.