你即將離開本站

並前往https://aclanthology.org/2021.findings-acl.121.pdf

Infusing Knowledge into Pre-Trained Models with Adapters

the historically injected knowledge would be flushed away. To address this, we propose K-. ADAPTER, a framework that retains the origi-.

確定！ 回上一頁

查詢 「K-Adapter」的人也找了：

  1. K adapter GitHub
    2.
  2. Transformer adapter
    3.
  3. K-BERT
    4.
  4. KEPLER: a unified model for knowledge embedding and pre trained language representation
    5.
  5. SenseBERT
    6.
  6. Knowledge Enhanced Contextual Word Representations
    7.
  7. Parameter-Efficient Transfer Learning for NLP
    8.
  8. ERNIE paper
    9.