🧑‍🔬 Zdeněk Žabokrtský

🏛️ Affiliations

🎓Charles UniversityPrague · Czechia2001–2026 · 88 papersEmployment since 2001current🎓University of West Bohemia in PilsenPilsen · Czechia2024–2026 · 3 paperscurrent🎓Czech Technical University in PraguePrague · Czechia2000–2001 · 3 papers

🏛️Charles University, Faculty of Mathematics and PhysisPrague · Czechia2001Employment since 2001 · associate professor, Institute of Formal and Applied Linguistics

🏛️Faculty of Mathematics and Physics, Charles UniversityPrague · CzechiaEmployment

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Topics

🔗 Coreference resolution (9)🌐 Universal Dependencies (4)🌍 Multilingual & cross-lingual NLP (4)📏 Evaluation & benchmarks (3)📐 Syntax & grammar formalisms (3)🗂️ Treebanks (2)🔁 Machine translation (2)🧩 Morphology (1)🐪 Semitic languages (1)

📅 Works by year

2020s

2010s

2000s

📄 Papers

The most cited first (OpenAlex and our library).

1. Coordination Structures in Dependency Treebanks (2013 · 65 citations)
   A dependency tree cannot show the symmetric relation between conjuncts without a convention, so every treebank picks one.
2. Udapi: Universal API for Universal Dependencies (2017 · 61 citations)
   As UD and the CoNLL-U format spread, ad hoc scripts for processing treebanks became a common source of subtle bugs, such as forgetting to renumber nodes after a deletion.
3. CorefUD 1.0: Coreference Meets Universal Dependencies (2022 · 48 citations)
   Syntax has a shared multilingual annotation standard in Universal Dependencies, but coreference resolution has had no comparable standard: corpora define the phenomena differently and use different formats, so most systems are evaluated only on English OntoNotes.
4. Cross-lingual Coreference Resolution of Pronouns (2014 · 31 citations)
   Novák and Žabokrtský study coreference resolution (CR) on a bitext. Their goal is to resolve English 3rd-person central pronouns (personal, possessive and reflexive) more accurately by drawing on the aligned Czech translation. The two languages handle pronouns differently. Czech has grammatical gender, drops subject…
5. Hidden Markov Tree Model in Dependency-based Machine Translation (2009 · 30 citations)
   The paper applies Hidden Markov Tree Models (HMTM), a tree version of the hidden Markov chain, to the transfer step of a tree-based MT system.
6. Translation of "It" in a Deep Syntax Framework (2013 · 29 citations)
   English "it" has no single Czech counterpart. It may be a personal pronoun or zero anaphor, a neuter demonstrative "to", or nothing at all in a cleft or pleonastic construction. The paper builds a discriminative classifier for these three classes inside the TectoMT deep-syntax system. The training data is the Prague…
7. Formemes in English-Czech Deep Syntactic MT (2012 · 28 citations)
   A formeme is a short label for the surface morpho-syntax of a node in a deep dependency tree. It has three parts: a syntactic part of speech, an optional preposition or conjunction, and a form such as a case number or a finite-clause marker. The paper revises the formemes used in the TectoMT English-Czech system to…
8. Findings of the Second Shared Task on Multilingual Coreference Resolution (2023 · 27 citations)
   This paper describes the second round of the multilingual coreference resolution shared task, held with CRAC 2023.
9. Arabic Syntactic Trees: from Constituency to Dependency (2003 · 26 citations)
   The note reports work in progress on converting Penn-style phrase-structure trees of Arabic (from the LDC Arabic Treebank) into the analytical dependency trees of the Prague school.
10. Comparison of Classification and Ranking Approaches to Pronominal Anaphora Resolution in Czech (2009 · 16 citations)
    The paper addresses resolving third-person personal and possessive pronouns in Czech, including zero (pro-dropped) pronouns that are reconstructed in the deep-syntactic layer.
11. Projection-based Coreference Resolution Using Deep Syntax (2017 · 14 citations)
    The paper addresses coreference resolution for German and Russian when no coreference-annotated data exist in those languages.
12. Coreference meets Universal Dependencies – a pilot experiment on harmonizing coreference datasets for 11 languages (2021 · 11 citations)
    The report converts 17 existing coreference datasets for 11 languages into one scheme based on Universal Dependencies.
13. Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches? (2025 · 10 citations)
    This overview reports the fourth edition of the multilingual coreference shared task at CODI-CRAC 2025. Participants had to detect mentions, including zero mentions in pro-drop languages, and cluster them by identity coreference. The data came from CorefUD 1.3, with 22 datasets in 17 languages used in the task; new…
14. Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities (2026 · 6 citations)
    The fifth edition of the multilingual coreference shared task, held with CODI-CRAC 2026, again asked for mention detection and identity coreference clustering.
15. Towards Universal Segmentations: UniSegments 1.0 (2022 · 6 citations)
    Plenty of annotated data already exists for morphological segmentation, that is, dividing a word form into morphs.
16. A Machine Learning Approach to Automatic Functor Assignment in the Prague Dependency Treebank (2002 · 4 citations)
    Converting analytical tree structures (ATS) into tectogrammatical tree structures (TGTS) in the Prague Dependency Treebank (PDT) requires a great deal of manual work by expert linguists.
17. Do UD Trees Match Mention Spans in Coreference Annotations? (2021 · 3 citations)
    Coreference mention spans in most corpora are plain token intervals, drawn without reference to syntax. The paper asks how often those spans match the subtrees of UD trees. It hand-checks mismatches in nine CorefUD datasets for eight languages. In eight of the nine, the trees come from UDPipe; English-GUM is the only…

Also in our library

8 more works of theirs are in our library without a page here yet; they will appear as we publish them.

🤝 Co-authors here

12 of 16 co-authors with a page, the most papers together first.

• Martin Popel ×10
• Michal Novák ×10
• Anna Nedoluzhko ×8
• Daniel Zeman ×7
• Jakub Sido ×3
• Miloslav Konopik ×3
• Ondrej Prazak ×3
• David Mareček ×2
• Milan Straka ×2
• Amir Zeldes
• Jan Štěpánek
• Maciej Ogrodniczuk

🔗 Cited by

Papers of our library cite their works 342 times (of the 140,884 papers whose bibliographies we read); 52 citing papers with a page here →.

↑ back to top

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