--- title: "'The parse is darc and full of errors — paper by Yu et al. (2017)" description: "The authors built two simple parsers for the CoNLL 2017 UD task: darc, a transition-based arc-standard… 2 references, cited by 2 papers here." authors: ["Kuan Yu", "Pavel Sofroniev", "Erik Schill", "Erhard Hinrichs"] year: 2017 venue: "Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies" source: "https://aclanthology.org/K17-3013/" doi: "10.18653/v1/k17-3013" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/yu-2017-parse-is-darc-full-errors/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yu-2017-parse-is-darc-full-errors/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/4/) / 'The parse is darc and full of errors: Universal dependency parsing with transition-based and graph-based algorithms' # 'The parse is darc and full of errors: Universal dependency parsing with transition-based and graph-based algorithms' Paper · 2017 · Kuan Yu, Pavel Sofroniev, Erik Schill et al. **Authors:** Kuan Yu, Pavel Sofroniev, Erik Schill and [Erhard Hinrichs](https://md.research.elamur.ai/free/en/authors/erhard-hinrichs/) · **Year:** 2017 · **Venue:** Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies **Link:** [aclanthology.org/K17-3013](https://aclanthology.org/K17-3013/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) [**4** citations OpenAlex, 2026-10-14](https://openalex.org/works?filter=cites:W2740805311) · [Cited by **2** papers in our library of the 141,840 papers whose bibliographies we read](https://md.research.elamur.ai/free/en/papers/yu-2017-parse-is-darc-full-errors/cited-by/) · [Conference on Computational Natural Language Learning (CoNLL)](https://md.research.elamur.ai/free/en/venues/conll/) · [CoNLL 2017](https://md.research.elamur.ai/free/en/venues/conll/2017/) — Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies · published by [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · [licence](https://creativecommons.org/licenses/by/4.0/) - [Publisher's page](https://aclanthology.org/K17-3013/) - [PDF](https://aclanthology.org/K17-3013.pdf) - [DOI 10.18653/v1/k17-3013](https://doi.org/10.18653/v1/k17-3013) - [OpenAlex](https://openalex.org/W2740805311) **Authors (4)** 1. [Kuan Yu](https://openalex.org/A5075175698) [Semantic Scholar](https://www.semanticscholar.org/author/2114077896) · h 2 · 35 citations · 2 works 2. [Pavel Sofroniev](https://openalex.org/A5009651303) [Semantic Scholar](https://www.semanticscholar.org/author/9549423) · h 4 · 88 citations · 9 works 3. [Erik Schill](https://openalex.org/A5022063874) [Semantic Scholar](https://www.semanticscholar.org/author/82232436) · h 1 · 5 citations · 2 works 4. [Erhard Hinrichs](https://openalex.org/A5108637841) [Semantic Scholar](https://www.semanticscholar.org/author/2576664) · h 22 · 2,087 citations · 149 works Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart. ## What it is about The authors built two simple parsers for the CoNLL 2017 UD task: darc, a transition-based arc-standard parser with a swap action and a feedforward network, which was the official system and ranked 12th of 33, and mstnn, a graph-based parser that was not ranked. The paper is a post-mortem: it asks why the simple parser lands just above the baseline. The explanations are that the pipeline errors snowball, that using lemmas where they exist helped the lexical space, that treating FEATS as atomic symbols causes sparsity, and that training on the full training sets beat the baseline's split. mstnn lost about four points more from UAS to LAS than darc did, which the authors read as the cost of its separate labeller in a pipeline. ## For Mova - I1. Tagger-cost measure: run `en parse-eval` on EWT dev with gold UPOS and FEATS and with predicted ones; the LAS gap is what the tagging stage costs the parser, and should be reported before any parser change, following the snowball argument. - I2. Lemma as a second lexical space in `en/src/parse.rs`: add the `en/src/morph.rs` lemma as a feature beside FORM and split the feature table between them, as darc does; measure EWT dev LAS against the current FORM-only features. - I3. FEATS as key-value backoff: in `en/src/ud.rs` back off from a full FEATS bundle to single key-value pairs; count types and hapax on EWT train, then measure UFeats and LAS on EWT dev (test only once per release). The parser is `en/src/parse.rs` (arc-standard, averaged perceptron, beam 8), the morphology is `en/src/morph.rs` and `en/src/ud.rs`, and the evaluation is `en parse-eval`. The chapter is [languages/en/13-verbs.md](https://mova.elamur.ai/free/en/docs/languages/en/13-verbs/) for the FEATS side and [languages/en/20-syntax-overview.md](https://mova.elamur.ai/free/en/docs/languages/en/20-syntax-overview/) for the parser. Measure first the tagger-cost gap on EWT dev. ## Institutions [🎓**University of Tübingen** Tübingen · Germany 30 works · 40,834 citations](https://md.research.elamur.ai/free/en/universities/university-of-tubingen/) ## Fields, topics and concepts 📚 Shelves 4 The field of science this work belongs to (OpenAlex fields).[Computer Science · 9,085 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 8,888 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 9,296 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 9,206 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 3 Research subjects and languages the work is about.[English · 1,373 works](https://md.research.elamur.ai/free/en/topics/english/) · [Dependency parsing · 120 works](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) · [Universal Dependencies · 174 works](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) ## Cite Cite as Kuan Yu, Pavel Sofroniev, Erik Schill and Erhard Hinrichs. 2017. 'The parse is darc and full of errors: Universal dependency parsing with transition-based and graph-based algorithms'. Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/k17-3013](https://doi.org/10.18653/v1/k17-3013) ```bibtex @inproceedings{yu2017parse, title = {{'The parse is darc and full of errors: Universal dependency parsing with transition-based and graph-based algorithms'}}, author = {Kuan Yu, Pavel Sofroniev, Erik Schill and Erhard Hinrichs}, booktitle = {Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies}, year = {2017}, doi = {10.18653/v1/k17-3013}, url = {https://doi.org/10.18653/v1/k17-3013} } ``` - [← previous Recognizing Textual Entailment in Twitter Using Word Embeddings](https://md.research.elamur.ai/free/en/papers/sulea-2017-recognizing-textual-entailment-twitter-word/) - [next → ARAACOM: ARAbic Algerian Corpus for Opinion Mining](https://md.research.elamur.ai/free/en/papers/abdelhafid-2020-araacom-arabic-algerian-corpus-opinion/) - [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/4/) ## References 2 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Our representation is explained in Section 3.2. We experimented with normalizing the FEATS vectors into unit vectors by their L 2 -norm, or into probability distributions by their L 1 -norm as in Alberti et al. (2015). But simple binary indicators seemed to work the best. [find](https://scholar.google.com/scholar?q=Our+representation+is+explained+in+Section+3%2E2%2E+We+experimented+with+normalizing+the+FEATS+vectors+into+unit+vectors+by+their+L+2+%2Dnorm%2C+or+into+probability+distributions+by+their+L+1+%2Dnorm+as+in+Albe) 2. Martı́n Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenbe… [find](https://scholar.google.com/scholar?q=Mart%C4%B1%CC%81n+Abadi%2C+Ashish+Agarwal%2C+Paul+Barham%2C+Eugene+Brevdo%2C+Zhifeng+Chen%2C+Craig+Citro%2C+Greg+S%2E+Corrado%2C+Andy+Davis%2C+Jeffrey+Dean%2C+Matthieu+Devin%2C+Sanjay+Ghemawat%2C+Ian+Goodfellow%2C+Andrew+Harp%2C+Geoffrey+) Updated 24 October 2026