[
  {
    "file": "fig1-03.png",
    "page": 3,
    "label": "Figure 1",
    "caption": "The Transformer - model architecture."
  },
  {
    "file": "fig2-04.png",
    "page": 4,
    "label": "Figure 2",
    "caption": "(left) Scaled Dot-Product Attention. (right) Multi-Head Attention consists of several attention layers running in parallel."
  },
  {
    "file": "table2-08.png",
    "page": 8,
    "label": "Table 2",
    "caption": "The Transformer achieves better BLEU scores than previous state-of-the-art models on the English-to-German and English-to-French newstest2014 tests at a fraction of the training cost."
  },
  {
    "file": "fig3-13.png",
    "page": 13,
    "label": "Figure 3",
    "caption": "An example of the attention mechanism following long-distance dependencies in the encoder self-attention in layer 5 of 6. Many of the attention heads attend to a distant dependency of the verb 'making', completing the phrase 'making...more difficult'. Attentions here shown only for the word 'making'. Different colors represent different heads. Best viewed in color."
  }
]