论文标题
通过增量元自我训练的半监督关系提取
Semi-supervised Relation Extraction via Incremental Meta Self-Training
论文作者
论文摘要
为了减轻人类从获得大规模注释中的努力，半监督的关系提取方法旨在除了从有限的样本中学习外，还旨在利用未标记的数据。现有的自我训练方法遇到了逐渐漂移问题，在训练过程中，在未标记的数据上纳入了嘈杂的伪标签。为了减轻伪标签中的噪声，我们提出了一种称为Metasre的方法，该方法通过（Meta）从成功和失败的关系分类网络中学习作为额外的元主体来对伪标签产生质量评估。为了减少嘈杂的伪标签的影响，Metasre采用了伪标签的选择和剥削方案，该方案评估了未标记的样品上的伪标签质量，并且仅利用自我培训方式来利用高质量的伪标签，以增强标签样品的稳健性和准确性。两个公共数据集的实验结果证明了拟议方法的有效性。
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.
