知识库完成符合迁移学习
Knowledge Base Completion Meets Transfer Learning
摘要：
知识库补全的目的是从知识库中现有的事实预测未知的事实。在这项工作中，我们介绍了第一种方法的知识转移从一个事实集合到另一个，而不需要实体或关系匹配。该方法适用于规范化的知识库和非规范化的或开放的知识库，即，知识库，其中可能存在真实世界实体或关系的多个副本。这种知识库是从非结构化文本中提取结构化数据的自动信息抽取工具的自然输出。我们的主要贡献是一种方法，可以利用从非结构化文本中收集的事实进行大规模的预训练，以提高对特定领域结构化数据的预测。引入的方法对ReVerb 20 K等小数据集最有影响力，尽管不依赖于BERT等大型预训练模型，但与之前的最佳方法相比，我们获得了平均倒数秩的6%绝对增加和平均秩的65%相对减少。
英文摘要：
The aim of knowledge base completion is to predict unseen facts from existing facts in knowledge bases. In this work, we introduce the first approach for transfer of knowledge from one collection of facts to another without the need for entity or relation matching. The method works for both canonicalized knowledge bases and uncanonicalized or open knowledge bases, i.e., knowledge bases where more than one copy of a real-world entity or relation may exist. Such knowledge bases are a natural output of automated information extraction tools that extract structured data from unstructured text. Our main contribution is a method that can make use of a large-scale pre-training on facts, collected from unstructured text, to improve predictions on structured data from a specific domain. The introduced method is the most impactful on small datasets such as ReVerb20K, where we obtained 6% absolute increase of mean reciprocal rank and 65% relative decrease of mean rank over the previously best method, despite not relying on large pre-trained models like BERT.
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。
