Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Kartchner, David"'
We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete.
Externí odkaz:
http://arxiv.org/abs/2010.04582
The success of deep neural networks has inspired many to wonder whether other learners could benefit from deep, layered architectures. We present a general framework called forward thinking for deep learning that generalizes the architectural flexibi
Externí odkaz:
http://arxiv.org/abs/1705.07366