Adversarial Training for Commonsense Inference
Ochanomizu University（御茶水女子大学）；Microsoft Research（微软研究院）；Kyoto University（京都大学）；The National Institute for Japanese Language and Linguistics (NINJAL)（日本国立国语研究所）
英文摘要：
We propose an AdversariaL training algorithm for commonsense InferenCE (ALICE). We apply small perturbations to word embeddings and minimize the resultant adversarial risk to regularize the model. We exploit a novel combination of two different approaches to estimate these perturbations: 1) using the true label and 2) using the model prediction. Without relying on any human-crafted features, knowledge bases, or additional datasets other than the target datasets, our model boosts the fine-tuning performance of RoBERTa, achieving competitive results on multiple reading comprehension datasets that require commonsense inference.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
