Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Daniel Zeman

Daniel Zeman

20 paper cards in Mova's library · 2012–2026

Daniel Zeman wrote 20 of the papers Mova reads, in 2012–2026, most of them on Universal Dependencies, Treebanks, Coreference resolution; often with Martin Popel, Anna Nedoluzhko, Zdeněk Žabokrtský.

OpenAlex · ORCID · h-index 28 · 4506 citations · 176 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Universal Dependencies 12 · Treebanks 8 · Coreference resolution 5 · Machine translation 4 · Part-of-speech tagging 2 · Dependency parsing 1

Papers

  1. Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities (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. First Shared Task on UMR Parsing (2026)
    The paper sets up the first shared task on UMR parsing. A system gets plain text and must return sentence-level graphs, the alignment of each node to tokens, and document-level relations such as coreference, temporal and modal links. Seven languages from four families take part: Indo-European, Sino-Tibetan, Na-Dene…
  3. Word Alignment-Based Evaluation of Uniform Meaning Representations (2026)
    Graph comparison, such as Smatch, forces every node of one graph onto a node of the other, even when the two nodes are unrelated, so the mismatch scores say little.
  4. Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches? (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…
  5. Bootstrapping UMRs from Universal Dependencies for Scalable Multilingual Annotation (2025)
    UMR annotation is slow, so the paper converts Universal Dependencies trees into partial UMR graphs that annotators then correct.
  6. CorefUD 1.0: Coreference Meets Universal Dependencies (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.
  7. Universal Dependencies (2021)
    This article sets out the linguistic theory behind Universal Dependencies (UD), which is at once a cross-linguistically consistent morphosyntactic annotation scheme, an open research community and a growing collection of treebanks.
  8. From Raw Text to Enhanced Universal Dependencies: The Parsing Shared Task at IWPT 2021 (2021)
    The shared task asks systems to parse raw text all the way to Enhanced Universal Dependencies (EUD), the graph layer that adds propagated conjuncts, controlled subjects, relative-clause antecedents, gapping and orphans.
  9. Coreference meets Universal Dependencies – a pilot experiment on harmonizing coreference datasets for 11 languages (2021)
    The report converts 17 existing coreference datasets for 11 languages into one scheme based on Universal Dependencies.
  10. Do UD Trees Match Mention Spans in Coreference Annotations? (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…
  11. Overview of the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies (2020)
    The overview introduces the task of parsing raw text into enhanced UD graphs, where a word may have several heads, graphs may contain cycles, and empty nodes may appear, for 17 languages.
  12. Estimating POS Annotation Consistency of Different Treebanks in a Language (2020)
    The paper asks whether several treebanks of the same language, all nominally following the Universal Dependencies guidelines, actually tag parts of speech in the same way.
  13. Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection (2020)
    The paper describes the UD v2 guidelines and the state of the collection at release 2.5: 157 treebanks in 90 languages, built by more than 300 contributors.
  14. CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (2018)
    This overview describes the second CoNLL shared task on parsing raw text into UD. Systems start from raw text, with no gold segmentation or tags, and are scored on 82 test treebanks, with macro-averaged LAS and two new metrics, MLAS (labels plus morphological features) and BLEX (lemmas plus labels). Eight new…
  15. Mind the Gap: Data Enrichment in Dependency Parsing of Elliptical Constructions (2018)
    Gapping (for example "Mary won gold and Peter bronze") is rare in treebanks, so parsers learn it poorly: the orphan relation has almost no training examples.
  16. CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (2017)
    The shared task asks systems to parse raw text, with no gold tokenization, sentence splitting or tags, into UD trees for 49 languages.
  17. Universal Dependencies for Arabic (2017)
    The paper presents NUDAR, a Universal Dependencies treebank for Modern Standard Arabic of 738,889 tokens in 19,738 sentences, made by converting the Penn Arabic Treebank (parts 1–3).
  18. Universal Dependencies v1: A Multilingual Treebank Collection (2016)
    The paper is the reference for the first UD release. It sets out the design principles: dependency-based and lexicalist annotation, the recoverability principle (every syntactic word must map back to the raw text), content words as the backbone of the tree with function words as dependents, and a closed inventory of…
  19. Coordination Structures in Dependency Treebanks (2013)
    A dependency tree cannot show the symmetric relation between conjuncts without a convention, so every treebank picks one.
  20. Automatic MT Error Analysis: Hjerson Helping Addicter (2012)
    The paper presents an open-source tool for detailed MT error analysis. It joins two systems: Hjerson, the automatic classifier from Popović (2011), and Addicter, which brings alignment, a web interface and a corpus browser. Errors are found by comparing the output with the reference through a chosen word alignment…

Co-authors (85)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/daniel-zeman/