Models & Architecture
Encoder-Decoder
A model design with one half that reads and compresses the input and another that generates the output, common in translation.
An encoder-decoder, or sequence-to-sequence, architecture splits the work in two: the encoder digests the input into a compact internal representation, and the decoder turns that representation into the output one step at a time. It fits any task that maps one sequence to another, like translating a sentence or summarizing a document. The original transformer was an encoder-decoder, and many modern models use one half or the other.
Reference: Wikipedia: Encoder-Decoder
Related terms
Transformer
The neural network design behind almost every modern language model, built around a mechanism called attention.
Attention
A mechanism that lets a model focus on the most relevant parts of its input when producing each piece of output.
Machine Translation
Automatically translating text or speech from one language to another, one of the oldest goals of AI.
Large Language Model
A model trained on massive amounts of text that predicts and generates language, powering tools like ChatGPT and Claude.