🧑‍🔬 Filip Ilievski

🏛️ Affiliations

🎓Vrije Universiteit AmsterdamAmsterdam · Netherlands2013–2026 · 51 papersEducation 2013–2015 · Master of Science, Artificial IntelligenceEducation 2015–2019 · PhD, Computational Lexicology and Terminology LabEmployment 2019 · PostDoc, Computational Lexicology and Terminology LabEmployment since 2023 · Assistant Professor (Sr.), Computer Sciencecurrent🎓University of Southern CaliforniaLos Angeles · United States2020–2024 · 49 papersEmployment 2022–2023 · Research Assistant Professor, Computer Science🎓Harvard UniversityCambridge · United States2011–2013 · 10 papers

🏛️USC Information Sciences InstituteMarina del Rey · United States2019–2023Employment 2019–2022 · Computer ScientistEmployment 2022–2023 · Research Lead

🏛️Information Sciences InstituteCalifornia · United States2019Employment since 2019

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Representing Numbers in NLP: a Survey and a Vision (2021 · 139 citations)
   This survey addresses a gap in NLP: most systems handle numbers poorly. They either drop numbers during preprocessing, collapse them into UNK tokens, or let BPE/WordPiece break them into arbitrary pieces. Neuroscience, by contrast, suggests the brain processes quantities differently from words. The authors propose…
2. ARN: Analogical Reasoning on Narratives (2024 · 17 citations)
   Most NLP research on analogy tests word-pair proportions (A : B :: C : D). Cognitive psychology, by contrast, studies analogy mainly through stories and separates shallow overlap from deeper relational structure. The authors ask whether current LLMs can detect such structure-level ("system") analogies between…

All works

4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Representing Numbers in NLP: a Survey and a VisionConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Avijit Thawani, Jay Pujara, Filip Ilievski, et al.2021 · 139 citations
2. Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering ↗Findings of the Association for Computational Linguistics: EMNLP 2020 · no summary yetPeifeng Wang et al.2020 · 104 citations
3. Dimensions of Commonsense Knowledge ↗arXiv:2101.04640 (Knowledge-Based Systems 2021) · no summary yetFilip Ilievski et al.2021 · 94 citations
4. ARN: Analogical Reasoning on NarrativesTransactions of the Association for Computational Linguistics (TACL)Zhivar Sourati, Filip Ilievski, Pia Sommerauer, et al.2024 · 17 citations

🤝 Co-authors here

3 co-authors with a page, the most papers together first.

• Jay Pujara
• Yifan Jiang
• Zhivar Sourati

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2021
• Transactions of the Association for Computational Linguistics (TACL): Transactions of the Association for Computational Linguistics (TACL) 2024
• Findings of the Association for Computational Linguistics: EMNLP 2020

🔗 Cited by

Papers of our library cite their works 129 times (of the 149,439 papers whose bibliographies we read); 18 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/filip-ilievski/