论文标题
名字叫什么？伯特命名的实体表示形式是否对任何其他名称都有益？
What's in a Name? Are BERT Named Entity Representations just as Good for any other Name?
论文作者
论文摘要
我们通过研究了输入中同一类型类的替换，评估了基于BERT的NLP模型的命名实体表示。我们强调说，在几个任务上，尽管这种扰动是自然的，但受过训练的最先进的模型令人惊讶地脆弱。即使是最近感知的BERT模型，脆性仍在继续。我们还试图辨别这种非志愿性的原因，考虑到诸如令牌化和发生频率之类的因素。然后，我们提供了一种简单的方法，该方法可以从多个替换中进行预测，同时共同对类型注释和标签预测的不确定性进行建模。在三个NLP任务上进行的实验表明，我们的方法可以增强自然数据集和对抗数据集的鲁棒性并提高精度。
We evaluate named entity representations of BERT-based NLP models by investigating their robustness to replacements from the same typed class in the input. We highlight that on several tasks while such perturbations are natural, state of the art trained models are surprisingly brittle. The brittleness continues even with the recent entity-aware BERT models. We also try to discern the cause of this non-robustness, considering factors such as tokenization and frequency of occurrence. Then we provide a simple method that ensembles predictions from multiple replacements while jointly modeling the uncertainty of type annotations and label predictions. Experiments on three NLP tasks show that our method enhances robustness and increases accuracy on both natural and adversarial datasets.
