Multilingual Entity Linking Using Dense Retrieval
This work makes entity linking more accessible and reproducible for researchers and practitioners with limited resources, though it is incremental in improving efficiency and scalability.
The paper tackled the problem of expensive and non-reproducible entity linking systems by developing fast-to-train models using dense retrieval, achieving competitive performance across 9 languages without requiring large GPU clusters.
Entity linking (EL) is the computational process of connecting textual mentions to corresponding entities. Like many areas of natural language processing, the EL field has greatly benefited from deep learning, leading to significant performance improvements. However, present-day approaches are expensive to train and rely on diverse data sources, complicating their reproducibility. In this thesis, we develop multiple systems that are fast to train, demonstrating that competitive entity linking can be achieved without a large GPU cluster. Moreover, we train on a publicly available dataset, ensuring reproducibility and accessibility. Our models are evaluated for 9 languages giving an accurate overview of their strengths. Furthermore, we offer a~detailed analysis of bi-encoder training hyperparameters, a popular approach in EL, to guide their informed selection. Overall, our work shows that building competitive neural network based EL systems that operate in multiple languages is possible even with limited resources, thus making EL more approachable.