Filip Ilievski

Filip Ilievski is a Computer Scientist in the Center on Knowledge Graphs within the Information Sciences Institute (ISI) at the USC Viterbi School of Engineering. Prior to joining ISI, he obtained a Master degree in Computer Science and a Ph.D. in Natural Language Processing from the Vrije Universiteit (VU) in Amsterdam, under supervision of professors Piek Vossen and Frank van Harmelen. In 2017, Filip spent a semester as a research visitor at the Language Technologies Institute at Carnegie Mellon University (CMU), working with prof. Ed Hovy.

His principal research interest concerns the role of background knowledge for filling gaps in human communication, thus bridging ideas from Information Extraction, Knowledge Graphs, and Machine Learning. Filip’s dissertation, published as a book in the Studies in the Semantic Web series, explored how such knowledge can help to identify ‘long-tail’ entities in text, characterized by knowledge scarcity and ambiguity. He developed LOTUS, the largest publicly available index over the Linked Data cloud at the time, which received an award at the Semantics conference in 2016. At CMU, Filip worked on neural generalization models (‘profiling machines’) over formal knowledge and experimented with their utility to cluster long-tail entities in text. As part of his research on measuring and improving biases in NLP evaluations, he co-organized a SemEval competition on ‘Counting Events and Participants in the Long Tail’ in 2018.

Currently, Dr. Ilievski investigates how to represent commonsense knowledge sources and consolidate them in a single commonsense knowledge graph (CSKG), which is expected to enhance the ability of existing neural systems to answer natural language questions.