ISI Directory

Filip Ilievski, Ph.D

Computer Scientist

Education

Ph.D, Natural Language Processing, VU Amsterdam, The Netherlands
MSc., Artificial Intelligence, VU Amsterdam, The Netherlands
BSc., Computer Science, Ss. Cyril and Methodius University of Skopje, Macedonia

Bio

Since December 2019, I am a Computer Scientist in the Center on Knowledge Graphs within the Information Sciences Institute (ISI) at the USC Viterbi School of Engineering. My current mentor is Pedro Szekely. I hold a Ph.D. in Natural Language Processing from the Vrije Universiteit (VU) in Amsterdam. My Ph.D mentors were: Piek Vossen, Stefan Schlobach, Marieke van Erp, and Frank van Harmelen. My dissertation investigated the identity of long-tail entities in text. During a research visit at CMU in 2017, I worked under the supervision of Prof. Ed Hovy on inducing entity type profiles from knowledge graphs.

Research Summary

My principal research interest concerns the role of background knowledge for filling gaps in human communication. I am leading the development of the Commonsense Knowledge Graph (CSKG), a resource which consolidates existing sources into a harmonized representation. CSKG allows us to enhance language models for zero-shot Question Answering with more knowledge, precisely select relevant subsets, or perform explainable inference. I am also heavily involved in the development of the Knowledge Graph ToolKit (KGTK) - a comprehensive set of operations for working with modern, hyperrelational graphs like Wikidata. In the past year, I worked together with around 10 Ph.D. and Master students, and collaborated with researchers at CMU, Bosch Research, RPI, etc. We have been publishing this work in top-tier venues like AAAI, EMNLP, NAACL, and ISWC, and organizing commonsense workshops (AAAI’21) and tutorials (AAAI’21, ISWC’20, ISWC’21).