Explore Better Relative Position Embeddings from Encoding Perspective for Transformer Models

1 code implementation • EMNLP 2021 • Anlin Qu, Jianwei Niu, Shasha Mo

Relative position embedding (RPE) is a successful method to explicitly and efficaciously encode position information into Transformer models.

Key Mention Pairs Guided Document-Level Relation Extraction

no code implementations • COLING 2022 • Feng Jiang, Jianwei Niu, Shasha Mo, Shengda Fan

To this end, we propose a novel DocRE model called Key Mention pairs Guided Relation Extractor (KMGRE) to directly model mention-level relations, containing two modules: a mention-level relation extractor and a key instance classifier.

Document-level Relation Extraction

CETA: A Consensus Enhanced Training Approach for Denoising in Distantly Supervised Relation Extraction

1 code implementation • COLING 2022 • Ruri Liu, Shasha Mo, Jianwei Niu, Shengda Fan

This paper proposes a sentence-level DSRE method beyond typical instance selection approaches by preventing samples from falling into the wrong classification space on the feature space.

Classification Denoising +2

DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature Distributions

1 code implementation • CVPR 2021 • Yuntao Qu, Shasha Mo, Jianwei Niu

Firstly, methods based on the noise probability modeling can only be applied to class-level noisy labels.

Learning with noisy labels Memorization