Unified Examination of Entity Linking in Absence of Candidate Sets
This work addresses the problem of inconsistent evaluation in entity linking for researchers and practitioners, but it is incremental as it focuses on benchmarking and analysis rather than proposing a new method.
The paper tackles the lack of a unified comparative analysis of entity linking systems by introducing a black-box benchmark and evaluating state-of-the-art methods, finding that these systems heavily depend on candidate sets, which limits their general applicability, and showing that using the entire in-domain candidate set can substitute for certain models with trade-offs in inference time and memory.
Despite remarkable strides made in the development of entity linking systems in recent years, a comprehensive comparative analysis of these systems using a unified framework is notably absent. This paper addresses this oversight by introducing a new black-box benchmark and conducting a comprehensive evaluation of all state-of-the-art entity linking methods. We use an ablation study to investigate the impact of candidate sets on the performance of entity linking. Our findings uncover exactly how much such entity linking systems depend on candidate sets, and how much this limits the general applicability of each system. We present an alternative approach to candidate sets, demonstrating that leveraging the entire in-domain candidate set can serve as a viable substitute for certain models. We show the trade-off between less restrictive candidate sets, increased inference time and memory footprint for some models.