O'Reilly logo

Hands-On Natural Language Processing with Python by Rajalingappaa Shanmugamani, Rajesh Arumugam

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Encoder-decoder network

The most common types of architectures are encoder-decoder networks. These are similar to the one we used in the chapter on text summarization. In fact, the model architecture is not much different from the one we used there. The source text phrase is first fed into the encoder, which transforms it into a thought vector that represents the meaning of the phrase. This dense representation is then fed into a decoder, along with the original translation in the target language during training. It serves as a preconditioning on the decoder, which learns the corresponding translation based on the original translation that's fed while training.

The following diagram shows the encoder-decoder network as described in the paper ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required