Knowing false negatives: An adversarial training method for distantly supervised relation extraction
Distantly supervised relation extraction (RE) automatically aligns unstructured text with
relation instances in a knowledge base (KB). Due to the incompleteness of current KBs …
relation instances in a knowledge base (KB). Due to the incompleteness of current KBs …
Competition or cooperation? exploring unlabeled data via challenging minimax game for semi-supervised relation extraction
Abstract Semi-Supervised Relation Extraction aims at learning well-performed RE models
with limited labeled and large-scale unlabeled data. Existing methods mainly suffer from …
with limited labeled and large-scale unlabeled data. Existing methods mainly suffer from …
Noise-Tolerant Supervised Relation Extraction
H Xinbang, Y Hongtao, L Shaomei… - … Conference on Artificial …, 2021 - ieeexplore.ieee.org
Existing supervised relation extraction methods share generate flaws that they have
improvable feature extractors and are uncapable of eliminating task-irrelevant words. To …
improvable feature extractors and are uncapable of eliminating task-irrelevant words. To …