Abstract
Adversarial training (AT) is a regularization method that can be used to improve the robustness of neural network methods by adding small perturbations in the training data. We show how to use AT for the tasks of entity recognition and relation extraction. In particular, we demonstrate that applying AT to a general purpose baseline model for jointly extracting entities and relations, allows improving the state-of-the-art effectiveness on several datasets in different contexts (i.e., news, biomedical, and real estate data) and for different languages (English and Dutch).
Abstract (translated)
对抗训练(AT)是一种正则化方法,可以通过在训练数据中添加小扰动来提高神经网络方法的鲁棒性。我们展示了如何将AT用于实体识别和关系提取的任务。特别是,我们证明将AT应用于通用基线模型以联合提取实体和关系,可以改善不同环境中几个数据集(即新闻,生物医学和房地产数据)的最新效果。和不同的语言(英语和荷兰语)。
URL
https://arxiv.org/abs/1808.06876