[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/ud-2020-ek-how-much-enhanced-ud-is/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [English](https://md.mova.elamur.ai/free/en/docs/papers/en/) / How Much of Enhanced UD Is Contained in UD? # How Much of Enhanced UD Is Contained in UD? **Authors:** [Adam Ek](https://md.mova.elamur.ai/free/en/docs/papers/authors/adam-ek/), [Jean-Philippe Bernardy](https://md.mova.elamur.ai/free/en/docs/papers/authors/jean-philippe-bernardy/) · **Year:** 2020 · **Venue:** Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies **Link:** [aclanthology.org/2020.iwpt-1.23](https://aclanthology.org/2020.iwpt-1.23/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) [**6** citations](https://openalex.org/works?filter=cites:W3037749620) openalex-snapshot · 2026-10-14[**4** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/ud-2020-ek-how-much-enhanced-ud-is/) of the 140673 papers whose bibliographies we read[Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies](https://aclanthology.org/volumes/2020.iwpt-1/)[licence](https://creativecommons.org/licenses/by/4.0/) - [Publisher's page](https://aclanthology.org/2020.iwpt-1.23/) - [PDF](https://aclanthology.org/2020.iwpt-1.23.pdf) - [DOI 10.18653/v1/2020.iwpt-1.23](https://doi.org/10.18653/v1/2020.iwpt-1.23) - [OpenAlex](https://openalex.org/W3037749620) **Authors (2)** 1. Adam Ek [Semantic Scholar](https://www.semanticscholar.org/author/20493598) 2. [Jean-Philippe Bernardy](https://openalex.org/A5070681215) [ORCID](https://orcid.org/0000-0002-8469-5617) · [Semantic Scholar](https://www.semanticscholar.org/author/144701616) · h 15 · 774 citations · 90 works Citations and author metrics from openalex-snapshot (2026-10-14); authors with the same name are not always told apart. ## What it is about The CLASP submission to IWPT 2020 tests the hypothesis that enhanced UD (EUD) can be rebuilt from basic UD trees with a small set of tree-rewriting patterns. Five patterns cover conjunct propagation (for nsubj, obj, obl and similar relations), subject sharing for xcomp, relative-pronoun references, and case-enhanced labels such as obl:on. Each pattern matches a path of three nodes, two arcs in a row or two arcs leaving one node, with label conditions. On gold UD trees the rewriting gets ELAS 81.55 and EULAS 96.70 and misses under 4% of edges. On Stanza trees it reaches ELAS 67.85 and EULAS 80.18 in the official run, almost the same as using Stanza's own trees, so the basic parse errors on the relevant paths limit the result. The authors list what the rules cannot do: morphological case labels, multiword case words such as "so that", and ellipsis. ## Ideas - I1. `prag` / `world`: implement the conjunct-propagation and xcomp-subject patterns as tree-to-graph rules on Mova's gold dialect trees, and measure ELAS and EULAS on EWT dev; the paper's gold figures (81.55 and 96.70) are the starting point. - I2. Use the rules as a check on the converters: for each bank under `treebanks/en/`, the EUD derived from its gold trees should reach EULAS above 95 on dev, and a lower score means the converter lost information. - I3. Add the lemma of the case or mark dependent to obl, nmod, advcl and acl labels in the derived layer (the paper's case labels) and measure the ELAS gain on GUM test (test only). - I4. Decompose the ELAS loss of `en` against gold trees by pattern, to show whether the parser or the rewriting step limits the enhanced score. ## For Mova The paper's hypothesis matters for `prag` and `world`, which read UD trees into events and need the same kinds of relations (propagated conjuncts, controlled subjects, relative-clause antecedents). The ideas touch [24. Coordination and subordination](https://md.mova.elamur.ai/free/en/docs/languages/en/24-coordination-subordination/), `23-complementation.md` (control) and `25-relative-clauses.md`. Start with I1 and I2 on dev. Topics: [Universal Dependencies](https://md.mova.elamur.ai/free/en/docs/papers/topics/universal-dependencies/) ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/2020.iwpt-1.23](https://doi.org/10.18653/v1/2020.iwpt-1.23) ``` @inproceedings{ek2020how, title = {{How Much of Enhanced UD Is Contained in UD?}}, author = {Ek, Adam and Bernardy, Jean-Philippe}, booktitle = {Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies}, year = {2020}, doi = {10.18653/v1/2020.iwpt-1.23}, url = {https://doi.org/10.18653/v1/2020.iwpt-1.23} } ``` - [← previous Overview of the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies](https://md.mova.elamur.ai/free/en/docs/papers/ud-2020-bouma-overview-iwpt-2020-shared-task/) - [next → Integrating Graph-Based and Transition-Based Dependency Parsers in the Deep Contextualized Era](https://md.mova.elamur.ai/free/en/docs/papers/ud-2020-falenska-integrating-graph-based-transition-based/) - [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/) ## References 6 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Gosse Bouma, Djamé Seddah, and Daniel Zeman. 2020. Overview of the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, Seattle, US. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Gosse+Bouma%2C+Djame%CC%81+Seddah%2C+and+Daniel+Zeman%2E+2020%2E+Overview+of+the+IWPT+2020+Shared+Task+on+Parsing+into+Enhanced+Universal+Dependencies%2E+In+Proceedings+of+the+16th+International+Conference+on+Parsin) [our card](https://md.mova.elamur.ai/free/en/docs/papers/ud-2020-bouma-overview-iwpt-2020-shared-task/) 2. Timothy Dozat and Christopher D Manning. 2016. Deep biaffine attention for neural dependency parsing. arXiv preprint arXiv:1611.01734. [↗](https://arxiv.org/abs/1611.01734) [our card](https://md.mova.elamur.ai/free/en/docs/papers/missing-2016-dozat-deep-biaffine-attention-neural-dependency/) 3. Murhaf Fares, Stephan Oepen, Lilja Øvrelid, Jari Björne, and Richard Johansson. 2018. The 2018 shared task on extrinsic parser evaluation: on the downstream utility of english universal dependency parsers. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 22–33. [find](https://scholar.google.com/scholar?q=Murhaf+Fares%2C+Stephan+Oepen%2C+Lilja+%C3%98vrelid%2C+Jari+Bjo%CC%88rne%2C+and+Richard+Johansson%2E+2018%2E+The+2018+shared+task+on+extrinsic+parser+evaluation%3A+on+the+downstream+utility+of+english+universal+dependency+pa) [our card](https://md.mova.elamur.ai/free/en/docs/papers/ud-2018-fares-2018-shared-task-extrinsic-parser/) 4. David McClosky, Mihai Surdeanu, and Christopher D Manning. 2011. Event extraction as dependency parsing. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, pages 1626–1635. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=David+McClosky%2C+Mihai+Surdeanu%2C+and+Christopher+D+Manning%2E+2011%2E+Event+extraction+as+dependency+parsing%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%3A+Hum) 5. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D Manning. 2020. Stanza: A python natural language processing toolkit for many human languages. arXiv preprint arXiv:2003.07082. [↗](https://arxiv.org/abs/2003.07082) [our card](https://md.mova.elamur.ai/free/en/docs/papers/ud-2020-qi-stanza-python-natural-language-processing/) 6. Sebastian Schuster and Christopher D Manning. 2016. Enhanced english universal dependencies: An improved representation for natural language understanding tasks. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 2371–2378. [find](https://scholar.google.com/scholar?q=Sebastian+Schuster+and+Christopher+D+Manning%2E+2016%2E+Enhanced+english+universal+dependencies%3A+An+improved+representation+for+natural+language+understanding+tasks%2E+In+Proceedings+of+the+Tenth+Internatio) [our card](https://md.mova.elamur.ai/free/en/docs/papers/ud-2016-schuster-enhanced-english-universal-dependencies-improved/)