Supervised Understanding of Word Embeddings
[TOC]
論文網址
ICML 2020
black-box adversarial reprogramming (BAR)
Using zeroth order optimization and multi-label mapping techniques, BAR can reprogram a blackbox ML model solely based on its input-output responses without knowing the model architecture or changing any parameter
BAR also outperforms baseline transfer learning approaches by a significant margin, demonstrating cost-effective means and new insights for transfer learning.
references
NLP
論文
BERT 的sentence-based extractive model 通常extracte出多餘的或沒有訊息的summary 且 long dependency on document 也是一個問題(since bert pretrain is sentence-based)