论文标题
对比反对的自我监督的学习
Contrastive Self-Supervised Learning for Commonsense Reasoning
论文作者
论文摘要
我们提出了一种自我监督的方法，以解决代词歧义和Winograd模式挑战问题。我们的方法利用了与所谓的“触发”单词相关的培训语料库的特征结构，这些单词负责在代词歧义中翻转答案。我们通过构建成对的对比辅助预测来实现这种常识性推理。为此，我们利用通过对比度差的相互独家损失。我们的体系结构基于最近引入的变压器网络BERT，该网络在许多NLP基准测试中表现出很强的性能。经验结果表明，我们的方法减轻了当前监督方法的局限性。这项研究开辟了利用廉价的自我审议以实现常识性推理任务的绩效增长的途径。
We propose a self-supervised method to solve Pronoun Disambiguation and Winograd Schema Challenge problems. Our approach exploits the characteristic structure of training corpora related to so-called "trigger" words, which are responsible for flipping the answer in pronoun disambiguation. We achieve such commonsense reasoning by constructing pair-wise contrastive auxiliary predictions. To this end, we leverage a mutual exclusive loss regularized by a contrastive margin. Our architecture is based on the recently introduced transformer networks, BERT, that exhibits strong performance on many NLP benchmarks. Empirical results show that our method alleviates the limitation of current supervised approaches for commonsense reasoning. This study opens up avenues for exploiting inexpensive self-supervision to achieve performance gain in commonsense reasoning tasks.
