Conversa com Pedro Ruas (LASIGE, DI-FCUL).
Named Entity Linking systems are an essential component in Text Mining pipelines, bridging the gap between natural language (text) and knowledge bases. However, current systems have several limitations that affect their performance: the lack of context for entity mentions and approaches to deal with unlinkable entity mentions, incomplete disambiguation graphs, and excessive focus on English language to the detriment of multilingual approaches. The PhD project will focus on solving these challenges in order to develop a Named Entity Linking model that achieves state-of-the-art performance in Biomedical and Life Sciences domains.
Short Bio: He obtained the master's degree in Bioinformatics and Computational Biology (FCUL) in 2019, where his master's thesis was focused on improving a graph-based Named Entity Linking system applying the Personalized PageRank algorithm and semantic similarity. He joined the PhD in Informatics in October, 2020, and his main goal will be the development of Named Entity Linking systems that outperform state-of-the-art approaches.