Nov 7, 2021 · In this work, we strive to reconcile this gap and propose a robust learning framework named SCDL. (Self-Collaborative Denoising Learning).

Oct 9, 2021 · We propose a robust learning paradigm named Self-Collaborative Denoising Learning (SCDL), which jointly trains two teacher-student networks in a mutually- ...

Star 14. Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning. 14 stars 2 forks Branches Tags Activity · Star.

To address this issue, we propose a robust learning paradigm named Self-Collaborative Denoising Learning (SCDL), which jointly trains two teacher-student ...

For the incorrect annotation noise, previous works have suggested that the use of reinforcement learning and teacher-student framework is effective (Zhang et al ...

Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning ... Named Entity Recognition via Decomposed Framework.

Feb 15, 2023 · Improving Distantly-Supervised Named Entity Recognition with. Self-Collaborative Denoising Learning. Xinghua Zhang, Bowen Yu, Tingwen Liu ...

Feb 16, 2024 · Distantly-Supervised Named Entity Recognition (DS-NER) effectively alleviates the burden of annotation, but meanwhile suffers from the label ...

A self-adaptive learning framework termed SALO is proposed to improve the learning of NER models by dynamically incorporating adaptive label correction into ...

Distantly-Supervised Named Entity Recognition (DS-NER) effectively alleviates the data scarcity problem in NER by automatically generating training samples.