{
  "@context": "https://schema.org",
  "@type": "TechArticle",
  "@id": "https://anchorfact.org/kb/kb-2026-00284",
  "headline": "Attention vs. Self-Attention",
  "description": "Attention (Bahdanau 2014) computes relevance between encoder and decoder states — cross-attention. Self-Attention (Vaswani 2017) computes relevance within a single sequence — each position attends to all other positions. Self-attention enables the Transformer to capture long-range dependencies without recurrence.",
  "dateCreated": "2026-05-22T14:59:47.482Z",
  "dateModified": "2026-05-22T14:59:47.482Z",
  "author": {
    "@type": "Organization",
    "name": "AnchorFact"
  },
  "publisher": {
    "@type": "Organization",
    "name": "AnchorFact",
    "url": "https://anchorfact.org"
  },
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "anchorfact:confidence": "high",
  "anchorfact:generationMethod": "human_only",
  "citation": []
}