Semi-supervised Relation Extraction via Incremental Meta Self-Training

By Xuming Hu, Fukun Ma, Chenyao Liu, Chenwei Zhang, Lijie Wen, Philip S. Yu. 2020

89 citations recorded by the source corpus.

To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples. Existing self-training methods suffer from the gradual drift problem, where noisy pseudo labels on unlabeled data are incorporated during training. To alleviate the noise in pseudo labels, we propose a method called MetaSRE, where a Relation Label Generation Network generates accurate quality assessment on pseudo labels by (meta) learning from the successful and failed attempts on Relation Classification as an additional meta-objective. To reduce the influence of noisy pseudo labels, MetaSRE adopts a pseudo label selection and exploitation scheme which assesses pseudo label quality on unlabeled samples and only exploits high-quality pseudo labels in a self-training fashion to incrementally augment labeled samples for both robustness and accuracy. Experimental results on two public datasets demonstrate the effectiveness of the proposed approach.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chengwei Qin
2. Shafiq R. Joty
3. Zixuan Ke
4. Bin Liu

Citations in the corpus

• Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation (2022, background): “, 2014; Miwa and Bansal, 2016), semi-supervised (Chen et al., 2006; Sun et al., 2011; Hu et al., 2020) and distantly supervised methods (Mintz et al.”