Fast and Accurate Entity Linking via Graph Embedding

Entity Linking, the task of mapping ambiguous Named Entities to unique identifiers in a knowledge base, is a cornerstone of multiple Information Retrieval and Text Analysis systems. So far, no single entity linking algorithm has been able to offer the accuracy and scalability required to deal with the ever-increasing amount of data in the web and become a de-facto standard. In this paper, we propose a framework for entity linking that leverages graph embeddings to perform collective disambiguation. This framework is modular as it supports pluggable algorithms for embedding generation and candidate ranking. With our framework, we implement and evaluate a reference pipeline that uses DBpedia as knowledge base and leverages specific algorithms for fast candidate search and high-performance state-space search optimization. Compared to existing solutions, our approach offers state-of-the-art accuracy on a variety of datasets without any supervised training and provides real-time execution even when processing documents with dozens of Named Entities. Lastly, the flexibility of our framework allows adapting to a multitude of scenarios by balancing accuracy and execution time.