arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.09423cs.LG
收藏

ActKnow:低数据状态下问答的主动外部知识注入学习

ActKnow: Active External Knowledge Infusion Learning for Question Answering in Low Data Regime

Indian Institute of Science(印度科学理工学院)

K. M. Annervaz, Pritam Kumar Nath, Ambedkar Dukkipati

摘要:

深度学习模型在各种自然语言处理任务中设定了基准结果。然而,这些模型需要大量的训练数据,这在许多实际问题中是不可行的。虽然各种技术,如领域自适应,fewshot学习技术解决这个问题,我们引入了一种新的技术,积极注入外部知识学习,以解决低数据制度的问题。我们提出了一种称为ActKnow的技术,该技术积极地将基于知识图谱(KG)的知识“按需”注入到问答(QA)的学习中。通过注入来自Concept-Net的世界知识,我们在低数据状态下显示了对纯基于文本的Transformer模型(如RoBERTA)的ARC测试集基准的显着改进。例如,通过仅使用20%的训练样本,我们证明了ARC挑战和OpenBookQA的准确性分别提高了4%。

英文摘要:

Deep learning models have set benchmark results in various Natural Language Processing tasks. However, these models require an enormous amount of training data, which is infeasible in many practical problems. While various techniques like domain adaptation, fewshot learning techniques address this problem, we introduce a new technique of actively infusing external knowledge into learning to solve low data regime problems. We propose a technique called ActKnow that actively infuses knowledge from Knowledge Graphs (KG) based "on-demand" into learning for Question Answering (QA). By infusing world knowledge from Concept-Net, we show significant improvements on the ARC Challenge-set benchmark over purely text-based transformer models like RoBERTa in the low data regime. For example, by using only 20% training examples, we demonstrate a 4% improvement in the accuracy for both ARC-challenge and OpenBookQA, respectively.

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。

↑