Коллоквиум Neural Entity Linking: A Survey of Models Based on Deep Learning

In this talk, the speaker provides a brief survey of recent neural entity linking (EL) systems developed since 2015 as a result of the deep learning revolution in NLP. He systemizes design features of neural entity linking systems and compares their performances to the best classic methods on the common benchmarks distilling generic architectural components of a neural EL system, like candidate generation and entity ranking summarizing the prominent methods for each of them, such as approaches to mention encoding based on the selfattention architecture. Besides, various modifications of this general neural entity linking architecture can be grouped by several common themes: joint entity recognition and linking, models for global linking, domainindependent techniques including zeroshot and distant supervision methods, and crosslingual approaches. Since many neural models take advantage of pretrained entity embeddings to improve their generalization capabilities, I will also briefly discuss several types