Definition

Notation in a BERT-based Encoder-Decoder Architecture

In a BERT-based encoder-decoder architecture, specific mathematical notation is used to represent the sequences involved in the process. The source text is denoted as a sequence of tokens, x1...xmx_1...x_m, and its corresponding sequence of embeddings is represented as e1x...emx\mathbf{e}_{1}^{x}...\mathbf{e}_{m}^{x}. On the generation side, the target text sequence generated by the decoder is denoted as y1...yny_1...y_n, with its corresponding embedding sequence represented as e1y...eny\mathbf{e}_{1}^{y}...\mathbf{e}_{n}^{y}.

0

1

Updated 2026-04-18

Contributors are:

Who are from:

Tags

Ch.2 Generative Models - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

Ch.1 Pre-training - Foundations of Large Language Models