all AI news
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild. (arXiv:2305.07085v1 [cs.CL])
cs.CL updates on arXiv.org arxiv.org
The principle of continual relation extraction~(CRE) involves adapting to
emerging novel relations while preserving od knowledge. While current endeavors
in CRE succeed in preserving old knowledge, they tend to fail when exposed to
contaminated data streams. We assume this is attributed to their reliance on an
artificial hypothesis that the data stream has no annotation errors, which
hinders real-world applications for CRE. Considering the ubiquity of noisy
labels in real-world datasets, in this paper, we formalize a more practical
learning …
arxiv continual data data streams extraction knowledge noise novel relations reliance