BriefGPT.xyz
Apr, 2021
分享还是不分享：预测模型迁移学习的数据源集合
To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning
HTML
PDF
Lukas Lange, Jannik Strötgen, Heike Adel, Dietrich Klakow
TL;DR
通过模型迁移技术，使用支撑向量机算法并基于模型相似性，自动确定可用的多个数据源，以提高序列标注任务的性能，可以提高高达24个F1分数点。
Abstract
In low-resource settings,
model transfer
can help to overcome a lack of
labeled data
for many tasks and domains. However, predicting useful transfer sources is a challenging problem, as even the most similar sour
→