--- title: "A Statistical Parser for Czech — Collins 1999" description: "The paper asks how well a statistical parser built for English carries over to Czech." authors: ["Michael Collins", "Jan Hajic", "Lance Ramshaw", "Christoph Tillmann"] year: 1999 venue: "Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics" source: "https://aclanthology.org/P99-1065/" doi: "10.3115/1034678.1034754" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/collins-1999-statistical-parser-czech/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/collins-1999-statistical-parser-czech/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1999](https://md.research.elamur.ai/free/en/papers/1999/) / A Statistical Parser for Czech # A Statistical Parser for Czech **Authors:** [Michael Collins](https://md.research.elamur.ai/free/en/authors/michael-collins/), [Jan Hajic](https://md.research.elamur.ai/free/en/authors/jan-hajic/), [Lance Ramshaw](https://md.research.elamur.ai/free/en/authors/lance-ramshaw/), [Christoph Tillmann](https://md.research.elamur.ai/free/en/authors/christoph-tillmann/) · **Year:** 1999 · **Venue:** Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/) **Links:** [Publisher's page](https://aclanthology.org/P99-1065/) · [PDF](https://aclanthology.org/P99-1065.pdf) · [DOI 10.3115/1034678.1034754](https://doi.org/10.3115/1034678.1034754) · [OpenAlex](https://openalex.org/W2166451556) **Citations:** 193 citations (openalex-snapshot · 2026-10-14) · [87](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary The paper asks how well a statistical parser built for English carries over to Czech. Czech has rich inflection and fairly free word order, and other Slavic languages, Ukrainian among them, share both traits. The authors train on the Prague Dependency Treebank (PDT), which is annotated with dependencies rather than phrase structure. Their parser is lexicalized and adapts Model 1 of (Collins 97). Because that model expects lexicalized trees, they convert each dependency structure into a tree. Several trees can encode the same dependencies, so the conversion choices define the model's independence assumptions. A simple baseline uses flat trees, "XP" labels and coarse POS categories, and reaches about 72% dependency accuracy. Linguistically motivated changes to how relative clauses, coordination and punctuation are represented, together with changes to the model's parameterization, raise accuracy to about 80%. On news and business text the figure is roughly 82%. The same parser scores 91% on English WSJ text. The work shows that existing English methods can come reasonably close on a morphologically rich, free-order language. ## Key points - The PDT has about 480,000 words of general news, business and science text. It is split into a 19k-sentence training set plus development and evaluation sets of about 3,500 sentences each. - The Czech morphological analyzer can assign more than 3,000 tags. The PDT includes both manual and machine-assigned tags and lemmas. - Accuracy is measured as the share of correct dependency links. Each sentence has one link per token, counting an artificial root node. - On the development set, accuracy rose from 71.9% (baseline) to 79.3% (full model). Final results come from a held-out evaluation set that nobody saw during development, with about 80% overall. - Newswire text scored over 2% above the average. The Science section was clearly harder, likely because of longer sentences and more varied vocabulary. ## Interesting ideas - **Choose the conversion deliberately.** When dependency data feeds a phrase-structure parser, decide on purpose how flat the trees are, how nodes are labeled and which tagset is used. Each choice changes what the model treats as independent, which matters whenever data must be adapted to a tool built for another formalism. - **Relabel coordination by a conjunct.** The PDT makes the conjunction the head of a coordinated phrase. Labeling that phrase after its second conjunct, rather than the conjunction, recovers the phrase's real category. It also stops the model from happily joining two unlike phrases, which helps any treebank with conjunction-headed coordination. - **Back off instead of losing sentences.** When the full system finds no parse, the authors score the output of a simpler variant without bigrams. Sentences that still fail get all their words attached to the root. This keeps rare search failures from distorting the evaluation and suits any comparison of systems with uneven coverage. - **Report accuracy by genre.** Breaking results down by text type showed that science articles are much harder than news. This kind of reporting is useful when a corpus mixes domains. - **Separate syntactic and semantic relations.** As future work, the authors propose splitting word-word relations into tag-tag syntactic dependencies and lemma-lemma semantic dependencies, using the internal structure of rich tags. This looks promising against data sparsity in highly inflected languages such as Ukrainian. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/) ## Cited by Cited by 87 papers of our library cite it (of the 140884 whose bibliographies we read); 18 of them have a page here, 69 not yet. - [Corpus Variation and Parser Performance](https://md.research.elamur.ai/free/en/papers/aclbulk-2001-gildea-corpus-variation-parser-performance/) - [Better Arabic Parsing: Baselines, Evaluations, and Analysis](https://md.research.elamur.ai/free/en/papers/aclbulk-2010-green-better-arabic-parsing-baselines-evaluations/) - [Improving Arabic Dependency Parsing with Lexical and Inflectional Morphological Features](https://md.research.elamur.ai/free/en/papers/aclbulk-2010-marton-improving-arabic-dependency-parsing-lexical/) - [Morphological Features for Parsing Morphologically-rich Languages: A Case of Arabic](https://md.research.elamur.ai/free/en/papers/aclbulk-2011-dehdari-morphological-features-parsing-morphologically-rich/) - [Improving Arabic Dependency Parsing with Form-based and Functional Morphological Features](https://md.research.elamur.ai/free/en/papers/aclbulk-2011-marton-improving-arabic-dependency-parsing-form/) - [New Technologies for Old Germanic. Resources and Research on Parallel Bibles in Older Continental Western Germanic](https://md.research.elamur.ai/free/en/papers/chiarcos-2014-new-technologies-old-germanic-resources/) - [Head-Driven Statistical Models for Natural Language Parsing](https://md.research.elamur.ai/free/en/papers/cl-2003-collins-head-driven-statistical-models-natural/) - [Dependency Parsing of Modern Standard Arabic with Lexical and Inflectional Features](https://md.research.elamur.ai/free/en/papers/cl-2013-marton-dependency-parsing-modern-standard-arabic/) - [Online Learning of Approximate Dependency Parsing Algorithms](https://md.research.elamur.ai/free/en/papers/continual-2006-mcdonald-online-learning-approximate-dependency-parsing/) - [A Classifier of Word-Level Variants in Witnesses of Biblical Hebrew Manuscripts](https://md.research.elamur.ai/free/en/papers/findings-2025-stoupak-classifier-word-level-variants-witnesses/) - [Simple Semi-supervised Dependency Parsing](https://md.research.elamur.ai/free/en/papers/koo-2008-simple-semi-supervised-dependency-parsing/) - [Multi-Source Transfer of Delexicalized Dependency Parsers](https://md.research.elamur.ai/free/en/papers/mcdonald-2011-multi-source-transfer-delexicalized-dependency/) - [Non-Projective Dependency Parsing using Spanning Tree Algorithms](https://md.research.elamur.ai/free/en/papers/narrative-2005-mcdonald-non-projective-dependency-parsing-spanning/) - [Online Large-Margin Training of Dependency Parsers](https://md.research.elamur.ai/free/en/papers/narrative-2005-mcdonald-online-large-margin-training-dependency/) - [Pseudo-Projective Dependency Parsing](https://md.research.elamur.ai/free/en/papers/nivre-2005-pseudo-projective-dependency-parsing/) - [CoNLL-X Shared Task on Multilingual Dependency Parsing](https://md.research.elamur.ai/free/en/papers/parsers-2006-buchholz-conll-x-shared-task-multilingual/) - [Diachronic proximity vs. data sparsity in cross-lingual parser projection. A case study on Germanic](https://md.research.elamur.ai/free/en/papers/sukhareva-2014-diachronic-proximity-vs-data-sparsity/) - [Cross-Language Parser Adaptation between Related Languages](https://md.research.elamur.ai/free/en/papers/zeman-2008-cross-language-parser-adaptation-between/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{collins1999statistical, title = {{A Statistical Parser for Czech}}, author = {Collins, Michael and Hajic, Jan and Ramshaw, Lance and Tillmann, Christoph}, booktitle = {Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics}, year = {1999}, doi = {10.3115/1034678.1034754}, url = {https://doi.org/10.3115/1034678.1034754} } ``` - [next → An Efficient Method for Determining Bilingual Word Classes](https://md.research.elamur.ai/free/en/papers/och-1999-efficient-method-determining-bilingual-word/) - [↑ back to papers of 1999](https://md.research.elamur.ai/free/en/papers/1999/) ## References 13 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. E. Charniak. 1997. Statistical Parsing with a Context-free Grammar and Word Statistics. Proceedings of the Fourteenth National Conference on Artificial Intelligence, AAAI Press/MIT Press, Menlo Park (1997). [find](https://scholar.google.com/scholar?q=E%2E+Charniak%2E+1997%2E+Statistical+Parsing+with+a+Context%2Dfree+Grammar+and+Word+Statistics%2E+Proceedings+of+the+Fourteenth+National+Conference+on+Artificial+Intelligence%2C+AAAI+Press%2FMIT+Press%2C+Menlo+Park+%28) 2. M. Collins. 1996. A New Statistical Parser Based on Bigram Lexical Dependencies. Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics, pages 184-191. [find](https://scholar.google.com/scholar?q=M%2E+Collins%2E+1996%2E+A+New+Statistical+Parser+Based+on+Bigram+Lexical+Dependencies%2E+Proceedings+of+the+34th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+184%2D191%2E) 3. M. Collins. 1997. Three Generative, Lexicalised Models for Statistical Parsing. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, pages 16-23. [find](https://scholar.google.com/scholar?q=M%2E+Collins%2E+1997%2E+Three+Generative%2C+Lexicalised+Models+for+Statistical+Parsing%2E+In+Proceedings+of+the+35th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+8th+Conference+of+the+Eur) [our card](https://md.research.elamur.ai/free/en/papers/collins-1997-three-generative-lexicalised-models-statistical/) 4. M. Collins. 1999. Head-Driven Statistical Models for Natural Language Parsing. Ph.D. Thesis, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=M%2E+Collins%2E+1999%2E+Head%2DDriven+Statistical+Models+for+Natural+Language+Parsing%2E+Ph%2ED%2E+Thesis%2C+University+of+Pennsylvania%2E) 5. J. Eisner. 1996. Three New Probabilistic Models for Dependency Parsing: An Exploration. Proceedings of COLING-96, pages 340-345. [find](https://scholar.google.com/scholar?q=J%2E+Eisner%2E+1996%2E+Three+New+Probabilistic+Models+for+Dependency+Parsing%3A+An+Exploration%2E+Proceedings+of+COLING%2D96%2C+pages+340%2D345%2E) [our card](https://md.research.elamur.ai/free/en/papers/ast-1996-eisner-three-new-probabilistic-models-dependency/) 6. Jan Haji6. 1998. Building a Syntactically Annotated Corpus: The Prague Dependency Treebank. Issues of Valency and Meaning (Festschrift for Jarmila Panevov~i). Carolina, Charles University, Prague. pp. 106-132. [find](https://scholar.google.com/scholar?q=Jan+Haji6%2E+1998%2E+Building+a+Syntactically+Annotated+Corpus%3A+The+Prague+Dependency+Treebank%2E+Issues+of+Valency+and+Meaning+%28Festschrift+for+Jarmila+Panevov%7Ei%29%2E+Carolina%2C+Charles+University%2C+Prague%2E+pp%2E) 7. Jan Haji~ and Barbora Hladk~i. 1997. Tagging of Inflective Languages: a Comparison. In Proceedings of the ANLP'97, pages 136--143, Washington, DC. [find](https://scholar.google.com/scholar?q=Jan+Haji%7E+and+Barbora+Hladk%7Ei%2E+1997%2E+Tagging+of+Inflective+Languages%3A+a+Comparison%2E+In+Proceedings+of+the+ANLP%2797%2C+pages+136%2D%2D143%2C+Washington%2C+DC%2E) 8. Jan Haji6 and Barbora Hladka. 1998. Tagging Inflective Languages: Prediction of Morphological Categories for a Rich, Structured Tagset. In Proceedings of ACL/Coling'98, Montreal, Canada, Aug. 5-9, pp. 483-490. [find](https://scholar.google.com/scholar?q=Jan+Haji6+and+Barbora+Hladka%2E+1998%2E+Tagging+Inflective+Languages%3A+Prediction+of+Morphological+Categories+for+a+Rich%2C+Structured+Tagset%2E+In+Proceedings+of+ACL%2FColing%2798%2C+Montreal%2C+Canada%2C+Aug%2E+5%2D9%2C+pp%2E) 9. E Jelinek, J. Lafferty, D. Magerman, R. Mercer, A. Ratnaparkhi, S. Roukos. 1994. Decision Tree Parsing using a Hidden Derivation Model. Proceedings of the 1994 Human Language Technology Workshop, pages 272-277. [find](https://scholar.google.com/scholar?q=E+Jelinek%2C+J%2E+Lafferty%2C+D%2E+Magerman%2C+R%2E+Mercer%2C+A%2E+Ratnaparkhi%2C+S%2E+Roukos%2E+1994%2E+Decision+Tree+Parsing+using+a+Hidden+Derivation+Model%2E+Proceedings+of+the+1994+Human+Language+Technology+Workshop%2C+page) 10. V. Kubofi. 1999. A Robust Parser for Czech. Technical Report 6/1999, 0FAL, Matematicko-fyzikdlnf fakulta Karlovy univerzity, Prague. [find](https://scholar.google.com/scholar?q=V%2E+Kubofi%2E+1999%2E+A+Robust+Parser+for+Czech%2E+Technical+Report+6%2F1999%2C+0FAL%2C+Matematicko%2Dfyzikdlnf+fakulta+Karlovy+univerzity%2C+Prague%2E) 11. D. Magerman. 1995. Statistical Decision-Tree Models for Parsing. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, pages 276-283. [find](https://scholar.google.com/scholar?q=D%2E+Magerman%2E+1995%2E+Statistical+Decision%2DTree+Models+for+Parsing%2E+Proceedings+of+the+33rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+276%2D283%2E) [our card](https://md.research.elamur.ai/free/en/papers/magerman-1995-statistical-decision-tree-models-parsing/) 12. M. Marcus, B. Santorini and M. Marcinkiewicz. 1993. Building a Large Annotated Corpus of English: the Penn Treebank. Computational Linguistics, 19(2):313-330. [find](https://scholar.google.com/scholar?q=M%2E+Marcus%2C+B%2E+Santorini+and+M%2E+Marcinkiewicz%2E+1993%2E+Building+a+Large+Annotated+Corpus+of+English%3A+the+Penn+Treebank%2E+Computational+Linguistics%2C+19%282%29%3A313%2D330%2E) [our card](https://md.research.elamur.ai/free/en/papers/bank-1993-marcus-building-large-annotated-corpus-english/) 13. A. Ratnaparkhi. 1997. A Linear Observed Time Statistical Parser Based on Maximum Entropy Models. In Proceedings of the Second Conference [find](https://scholar.google.com/scholar?q=A%2E+Ratnaparkhi%2E+1997%2E+A+Linear+Observed+Time+Statistical+Parser+Based+on+Maximum+Entropy+Models%2E+In+Proceedings+of+the+Second+Conference)