Papers with noise-robust learning framework

1 papers
Enhancing Distantly Supervised Named Entity Recognition with Strong Label Guided Lottery Training (2024.lrec-main)

Copied to clipboard

Challenge: Named entity recognition (NER) requires a limited quantity of strongly labeled data . weakly labeles can be acquired through distant supervision, but can cause noise .
Approach: They propose a noise-robust learning framework where safe parameters can be identified . they conduct extensive experiments on multiple datasets and show it outperforms the state-of-the-art methods.
Outcome: The proposed framework outperforms the state-of-the-art methods on weakly labeled data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations