没有大哥哥或小哥哥：用于链接预测和问答的语言模型中的知识注入
There is No Big Brother or Small Brother: Knowledge Infusion in Language Models for Link Prediction and Question Answering
AI总结：
本文研究在航空、电影和Web领域向大型和小型语言模型注入知识以进行链接预测和问答，发现注入知识后小型模型表现与大型模型相似。
摘要：
知识图谱与深度学习的结合在提升各种自然语言处理（NLP）任务的性能方面正蓬勃发展。在本文中，我们重点关注在航空、电影和Web三个领域中使用语言模型、T5和BLOOM进行知识注入的链接预测和问答。在此背景下，我们将知识注入大型和小型语言模型中，并研究它们的性能，发现性能表现相似。对于Aviation Knowledge Graph上的链接预测任务，我们使用T5-small、T5-base、T5-large和BLOOM获得了0.2的hits@1分数。使用基于模板的脚本，我们从National Transportation Safety Board（NTSB）报告中创建了一组100万个航空领域的合成事实型QA对。在我们精选的QA对上，三种T5模型实现了0.7的hits@1分数。我们使用配对学生t检验和Cohen's kappa分数验证了我们的发现。对于使用T5-small和T5-large在Aviation Knowledge Graph上进行链接预测，我们获得了0.76的Cohen's kappa分数，表明模型之间存在实质性的一致性。因此，我们推断，在注入知识的情况下，小型语言模型的性能与大型语言模型相似。
英文摘要：
The integration of knowledge graphs with deep learning is thriving in improving the performance of various natural language processing (NLP) tasks. In this paper, we focus on knowledge-infused link prediction and question answering using language models, T5, and BLOOM across three domains: Aviation, Movie, and Web. In this context, we infuse knowledge in large and small language models and study their performance, and find the performance to be similar. For the link prediction task on the Aviation Knowledge Graph, we obtain a 0.2 hits@1 score using T5-small, T5-base, T5-large, and BLOOM. Using template-based scripts, we create a set of 1 million synthetic factoid QA pairs in the aviation domain from National Transportation Safety Board (NTSB) reports. On our curated QA pairs, the three models of T5 achieve a 0.7 hits@1 score. We validate out findings with the paired student t-test and Cohen's kappa scores. For link prediction on Aviation Knowledge Graph using T5-small and T5-large, we obtain a Cohen's kappa score of 0.76, showing substantial agreement between the models. Thus, we infer that small language models perform similar to large language models with the infusion of knowledge.
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。
