--- title: "Zdeněk Žabokrtský — papers and cards" description: "Zdeněk Žabokrtský: 10 paper cards in the Research library (2009–2026), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/zdenek-zabokrtsku/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zdenek-zabokrtsku/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Zdeněk Žabokrtský # Zdeněk Žabokrtský 10 paper cards in the Research library · 2009–2026 Zdeněk Žabokrtský wrote 10 of the papers Mova reads, in 2009–2026, most of them on [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/), [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/), [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/); often with [Martin Popel](https://md.research.elamur.ai/free/en/authors/martin-popel/), [Michal Novák](https://md.research.elamur.ai/free/en/authors/michal-novak/), [Anna Nedoluzhko](https://md.research.elamur.ai/free/en/authors/anna-nedoluzhko/). [OpenAlex](https://openalex.org/A5088317432) · [ORCID](https://orcid.org/0000-0001-8149-4054) · [**h-index 23**](https://openalex.org/authors/A5088317432) · [2044 citations](https://openalex.org/authors/A5088317432) · [167 works](https://openalex.org/works?filter=author.id:A5088317432) — openalex-snapshot, 2026-10-14 The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Zden%C4%9Bk+%C5%BDabokrtsk%C3%BD) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Zden%C4%9Bk+%C5%BDabokrtsk%C3%BD) · [dblp](https://dblp.org/search?q=Zden%C4%9Bk+%C5%BDabokrtsk%C3%BD) · [ACL Anthology](https://aclanthology.org/search/?q=Zden%C4%9Bk+%C5%BDabokrtsk%C3%BD) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Zden%C4%9Bk+%C5%BDabokrtsk%C3%BD) Topics: [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) 5 · [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) 4 · [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) 3 · [Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/) 2 · [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) 1 ## Papers 1. **[Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities](https://md.research.elamur.ai/free/en/papers/novak-2026-findings-fifth-shared-task-multilingual/)** *(2026)* The fifth edition of the multilingual coreference shared task, held with CODI-CRAC 2026, again asked for mention detection and identity coreference clustering. 2. **[Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?](https://md.research.elamur.ai/free/en/papers/novak-2025-findings-fourth-shared-task-multilingual/)** *(2025)* 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… 3. **[CorefUD 1.0: Coreference Meets Universal Dependencies](https://md.research.elamur.ai/free/en/papers/nedoluzhko-2022-corefud-1-0-coreference-meets/)** *(2022)* 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. **[Coreference meets Universal Dependencies – a pilot experiment on harmonizing coreference datasets for 11 languages](https://md.research.elamur.ai/free/en/papers/nedoluzhko-2021-coreference-meets-universal-dependencies/)** *(2021)* The report converts 17 existing coreference datasets for 11 languages into one scheme based on Universal Dependencies. 5. **[Do UD Trees Match Mention Spans in Coreference Annotations?](https://md.research.elamur.ai/free/en/papers/coref-2021-popel-do-ud-trees-match-mention/)** *(2021)* 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… 6. **[Udapi: Universal API for Universal Dependencies](https://md.research.elamur.ai/free/en/papers/popel-2017-udapi-universal-api-universal-dependencies/)** *(2017)* 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. 7. **[Coordination Structures in Dependency Treebanks](https://md.research.elamur.ai/free/en/papers/aclbulk-2013-popel-coordination-structures-dependency-treebanks/)** *(2013)* A dependency tree cannot show the symmetric relation between conjuncts without a convention, so every treebank picks one. 8. **[Translation of "It" in a Deep Syntax Framework](https://md.research.elamur.ai/free/en/papers/novak-2013-translation-it-deep-syntax-framework/)** *(2013)* 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… 9. **[Formemes in English-Czech Deep Syntactic MT](https://md.research.elamur.ai/free/en/papers/dusek-2012-formemes-english-czech-deep-syntactic/)** *(2012)* 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… 10. **[Hidden Markov Tree Model in Dependency-based Machine Translation](https://md.research.elamur.ai/free/en/papers/zabokrtsky-2009-hidden-markov-tree-model-dependency/)** *(2009)* 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. ## Co-authors (14) - [Martin Popel](https://md.research.elamur.ai/free/en/authors/martin-popel/) ×9 - [Michal Novák](https://md.research.elamur.ai/free/en/authors/michal-novak/) ×7 - [Anna Nedoluzhko](https://md.research.elamur.ai/free/en/authors/anna-nedoluzhko/) ×6 - [Daniel Zeman](https://md.research.elamur.ai/free/en/authors/daniel-zeman/) ×6 - [David Mareček](https://md.research.elamur.ai/free/en/authors/david-marecek/) ×2 - [Jakub Sido](https://md.research.elamur.ai/free/en/authors/jakub-sido/) ×2 - [Milan Straka](https://md.research.elamur.ai/free/en/authors/milan-straka/) ×2 - [Miloslav Konopík](https://md.research.elamur.ai/free/en/authors/miloslav-konopik/) ×2 - [Ondrej Prazak](https://md.research.elamur.ai/free/en/authors/ondrej-prazak/) ×2 - [Amir Zeldes](https://md.research.elamur.ai/free/en/authors/amir-zeldes/) - [Jan Štěpánek](https://md.research.elamur.ai/free/en/authors/jan-stepanek/) - Martin Majliš - Martin Vojtek - Ondřej Dušek ## More papers in the library (6) Pages of the Research library: our summary, the ideas, references and who cites each. - [Findings of the Second Shared Task on Multilingual Coreference Resolution](https://md.research.elamur.ai/free/en/papers/abokrtsky-2023-findings-second-shared-task-multilingual/) — Zdeněk Žabokrtský, Miloslav Konopik, Anna Nedoluzhko, et al. · 2023 - [Towards Universal Segmentations: UniSegments 1.0](https://md.research.elamur.ai/free/en/papers/abokrtsky-2022-universal-segmentations-unisegments-1-0/) — Zdeněk Žabokrtský, Niyati Bafna, Jan Bodnár, et al. · 2022 - [Projection-based Coreference Resolution Using Deep Syntax](https://md.research.elamur.ai/free/en/papers/novak-2017-projection-based-coreference-resolution-deep/) — Michal Novák, Anna Nedoluzhko, Zdeněk Žabokrtský · 2017 - [Cross-lingual Coreference Resolution of Pronouns](https://md.research.elamur.ai/free/en/papers/novak-2014-cross-lingual-coreference-resolution-pronouns/) — Michal Novák, Zdeněk Žabokrtský · 2014 - [Comparison of Classification and Ranking Approaches to Pronominal Anaphora Resolution in Czech](https://md.research.elamur.ai/free/en/papers/y-2009-comparison-classification-ranking-approaches-pronominal/) — Giang Linh Ngụy, Václav Novák, Zdeněk Žabokrtský · 2009 - [A Machine Learning Approach to Automatic Functor Assignment in the Prague Dependency Treebank](https://md.research.elamur.ai/free/en/papers/abokrtsky-2002-machine-learning-approach-automatic-functor/) — Zdeněk Žabokrtský, Petr Sgall, Sašo Džeroski · 2002