Knowledge Base Completion Meets Transfer Learning
This work addresses the challenge of improving knowledge base completion for small datasets, particularly in domains with limited structured data, by enabling transfer learning without entity or relation matching, though it is incremental as it builds on existing methods.
The paper tackles the problem of knowledge base completion by introducing a transfer learning approach that uses pre-training on facts from unstructured text to improve predictions on structured domain-specific data, achieving a 6% absolute increase in mean reciprocal rank and a 65% relative decrease in mean rank on the ReVerb20K dataset.
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.