Towards Making the Most of Pre-trained Translation Model for Quality Estimation

no code implementations • CCL 2022 • Li Chunyou, Di Hui, Huang Hui, Ouchi Kazushige, Chen Yufeng, Liu Jian, Xu Jinan

DR firstly introduces noise to the target side of parallel data, and the model is trained to detect and recover the introduced noise.

Denoising Language Modelling +4

Improving Low-Resource Named Entity Recognition via Label-Aware Data Augmentation and Curriculum Denoising

no code implementations • CCL 2021 • Zhu Wenjing, Liu Jian, Xu Jinan, Chen Yufeng, Zhang Yujie

“Deep neural networks have achieved state-of-the-art performances on named entity recognition(NER) with sufficient training data while they perform poorly in low-resource scenarios due to data scarcity.

Data Augmentation Denoising +5

Integrating Heterogeneous Information via Flexible Regularization Framework for Recommendation

no code implementations • 12 Nov 2015 • Shi Chuan, Liu Jian, Zhuang Fuzhen, Yu Philip S., Wu Bin

The experiments also reveal that different regularization models have obviously different impact on users and items.

Attribute