Semi-supervised Relation Extraction via Incremental Meta Self-Training
This work addresses a specific bottleneck in relation extraction for NLP researchers, offering an incremental improvement over existing self-training methods.
The paper tackles the problem of noisy pseudo labels in semi-supervised relation extraction by proposing MetaSRE, which uses a meta-learning approach to assess and select high-quality pseudo labels, resulting in improved robustness and accuracy on two public datasets.
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 quality assessment on pseudo labels by (meta) learning from the successful and failed attempts on Relation Classification Network 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.