In this work, we introduce and analyze an approach to knowledge transfer from one collection of facts to another without the need for entity or relation matching. The method works for both knowledge bases and or , i.e., knowledge bases where more than one copy of a real-world entity or relation may exist. The main contribution is a method that can make use of large-scale pre-training on facts, which were collected from unstructured text, to improve predictions on structured data from a specific domain. The introduced method is most impactful on small datasets such as , where a 6% absolute increase of mean reciprocal rank and 65% relative decrease of mean rank over the previously best method was achieved, despite not relying on large pre-trained models like . To understand the obtained pre-trained models better, we then introduce a novel dataset for the analysis of pre-trained models for Open Knowledge Base Completion, called (Diagnostics of Open knowledge Graph Embeddings). It consists of 6 subsets and is designed to measure multiple properties of a pre-trained model: robustness against synonyms, ability to perform deductive reasoning, presence of gender stereotypes, consistency with reverse relations, and coverage of different areas of general knowledge. Using the introduced dataset, we show that the existing OKBC models lack consistency in presence of synonyms and inverse relations and are unable to perform deductive reasoning. Moreover, their predictions often align with gender stereotypes, which persist even when presented with counterevidence. We additionally investigate the role of pre-trained word embeddings and demonstrate that avoiding biased word embeddings is not a sufficient measure to prevent biased behavior of OKBC models.

中文翻译：

---

预训练和诊断知识库补全模型

在这项工作中，我们介绍并分析了一种从一组事实到另一组事实的知识转移方法，无需实体或关系匹配。该方法适用于知识库 和 或 ，即可能存在多个现实世界实体或关系副本的知识库。主要贡献是一种可以利用从非结构化文本收集的事实的大规模预训练来改进对特定领域的结构化数据的预测的方法。所引入的方法对小型数据集影响最大，例如 ，尽管不依赖于像 这样的大型预训练模型，但与之前的最佳方法相比，平均倒数排名绝对增加了 6%，平均排名相对下降了 65%。为了更好地理解所获得的预训练模型，我们引入了一个新的数据集，用于分析开放知识库补全的预训练模型，称为（开放知识图嵌入诊断）。它由 6 个子集组成，旨在衡量预训练模型的多个属性：对同义词的鲁棒性、执行演绎推理的能力、性别刻板印象的存在、反向关系的一致性以及对不同领域常识的覆盖。使用引入的数据集，我们表明现有的 OKBC 模型在存在同义词和逆关系时缺乏一致性，并且无法执行演绎推理。此外，他们的预测通常与性别刻板印象相一致，即使有反证据，这种刻板印象也仍然存在。我们还研究了预训练词嵌入的作用，并证明避免有偏见的词嵌入并不足以防止 OKBC 模型的偏见行为。