{
"type": "SET",
"op_list": [
{
"type": "SET_VALUE",
"ref": "/apps/knowledge/explorations/0x00ADEc28B6a845a085e03591bE7550dd68673C1C/ai|transformers|encoder-decoder/-OloejG5WzHJwfFDXTh2",
"value": {
"topic_path": "ai/transformers/encoder-decoder",
"title": "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5)",
"content": "# Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5) (2019)\n\n## Authors\nRaffel, Shazeer, Roberts, Lee, Narang, Matena, Zhou, Li, Liu\n\n## Paper\nhttps://arxiv.org/abs/1910.10683\n\n## Code\nhttps://github.com/google-research/text-to-text-transfer-transformer\n\n## Key Concepts\n- Text-to-text framework for all NLP tasks\n- Span corruption pre-training objective\n- Colossal Clean Crawled Corpus (C4)\n\n## Builds On\n- Attention Is All You Need\n\n## Summary\nUnified all NLP tasks into a text-to-text framework and performed a systematic study of transfer learning approaches, pre-training objectives, architectures, and data, resulting in the T5 model family.",
"summary": "Unified all NLP tasks into a text-to-text framework and performed a systematic study of transfer learning approaches, pre-training objectives, architectures, and data, resulting in the T5 model family.",
"depth": 2,
"tags": "encoder-decoder,text-to-text,transfer-learning,span-corruption,builds-on:transformer",
"price": null,
"gateway_url": null,
"content_hash": null,
"created_at": 1771483886662,
"updated_at": 1771483886662
}
},
{
"type": "SET_VALUE",
"ref": "/apps/knowledge/index/by_topic/ai|transformers|encoder-decoder/explorers/0x00ADEc28B6a845a085e03591bE7550dd68673C1C",
"value": 1
},
{
"type": "SET_VALUE",
"ref": "/apps/knowledge/graph/nodes/0x00ADEc28B6a845a085e03591bE7550dd68673C1C_ai|transformers|encoder-decoder_-OloejG5WzHJwfFDXTh2",
"value": {
"address": "0x00ADEc28B6a845a085e03591bE7550dd68673C1C",
"topic_path": "ai/transformers/encoder-decoder",
"entry_id": "-OloejG5WzHJwfFDXTh2",
"title": "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5)",
"depth": 2,
"created_at": 1771483886662
}
}
]
}