--- title: "Experiments with a Multilanguage — Attardi 2006" description: "The paper presents a fast, multilingual dependency parser built for the CoNLL-X shared task." authors: ["Giuseppe Attardi"] year: 2006 venue: "Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X)" source: "https://aclanthology.org/W06-2922/" 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/attardi-2006-experiments-multilanguage-non-projective-dependency/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/attardi-2006-experiments-multilanguage-non-projective-dependency/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2006](https://md.research.elamur.ai/free/en/papers/2006/) / Experiments with a Multilanguage Non-Projective Dependency Parser # Experiments with a Multilanguage Non-Projective Dependency Parser **Authors:** [Giuseppe Attardi](https://md.research.elamur.ai/free/en/authors/giuseppe-attardi/) · **Year:** 2006 · **Venue:** Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X) · **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/W06-2922/) · [PDF](https://aclanthology.org/W06-2922.pdf) · [OpenAlex](https://openalex.org/W2161047600) **Citations:** 174 citations (openalex-snapshot · 2026-10-14) · [68](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary The paper presents a fast, multilingual dependency parser built for the CoNLL-X shared task. It targets two practical issues: the high training cost of accurate classifiers such as SVM, and the trees with crossing arcs (non-projective trees) that ordinary Shift/Reduce parsers cannot build. Attardi extends the deterministic bottom-up parser of Yamada and Matsumoto (2003) in two ways. First, it predicts dependency labels during parsing. Second, it adds six new actions (Right2/Left2, Right3/Left3, Extract/Insert) that link or temporarily set aside tokens deeper in the stack, so non-projective arcs are built directly instead of through pseudo-projective pre- and post-processing. The submitted runs used a custom C++ Maximum Entropy classifier with no external resources. Features were drawn from lemmas, coarse POS tags, a compact morphology token and previous actions. The parser processes about 200 sentences per second and needs minutes to hours to train. Memory Based Learning gives up to 5% higher accuracy but parses far more slowly. The work shows that a cheap, modular transition parser can cover all non-projectivity seen in the PDT and still stay practical. ## Key points - The new actions cover every non-projective case in the Czech training data. Of 28,081 such relations, 26,346 are handled by Left2/Right2, 1,683 by Left3/Right3, and only 52 require Extract/Insert. - With Maximum Entropy, training takes about 15 minutes for the Portuguese treebank and about 4 hours for Czech. Parsing averages roughly 200 sentences per second. - SVM (TinySVM, LIBSVM) was impractical. It could not be trained on the larger corpora, and on Portuguese it ran over 4 days and produced an unusable model. MBL trained faster and was up to 5% more accurate, but parsing was much slower. - Among the extra features tested, only including the previous parser action helped. Splitting the decision across two or three specialized classifiers brought no gain. - Assigning a default per-language label to the root raised LAS. The Snowball stemmer supplied LEMMA values for Danish, German and Swedish, which improved both accuracy and speed. ## Interesting ideas - **Extend the action set instead of transforming the data.** Adding reduce actions that reach the second or third stack element handles crossing arcs inside the parser itself. This avoids the lift-and-restore pipeline and could suit any transition system for free-word-order languages such as Ukrainian. - **Measure how often each mechanism is needed.** Counting which action each gold non-projective arc requires shows where effort pays off: most cases need only depth-2 actions. A coverage check of this kind is a cheap way to justify design choices in any structured predictor. - **Use a fast learner as a feature-engineering testbed.** Because one Maximum Entropy experiment on Portuguese took under 15 minutes, many feature sets could be tried quickly. The conclusions could then be carried over to slower, more accurate learners. - **Try a simple post-hoc fix.** Labelling the root with a per-language default gave a measurable LAS gain for almost no work. Similar targeted repairs could pay off elsewhere, for example stripping the PDT coordination and apposition suffixes (_Co, _Ap, _Pa) before training and restoring them afterwards. - **Give rare phenomena their own training data.** Non-projective arcs are too rare for a general classifier to learn well. The author suggests a dedicated second classifier and tested training on only the sentences with crossing arcs, which reached 65.28% LAS and 76.20% UAS on Czech with MBL. The same approach could help other rare structures or low-resource cases. *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: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) Topics: [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) ## Cited by Cited by 68 papers of our library cite it (of the 140673 whose bibliographies we read); 6 of them have a page here, 62 not yet. - [Top Accuracy and Fast Dependency Parsing is not a Contradiction](https://md.research.elamur.ai/free/en/papers/bohnet-2010-top-accuracy-fast-dependency-parsing/) - [Grammatical theory: From transformational grammar to constraint-based approaches](https://md.research.elamur.ai/free/en/papers/muller-2023-grammatical-theory-from-transformational/) - [Algorithms for Deterministic Incremental Dependency Parsing](https://md.research.elamur.ai/free/en/papers/narrative-2008-nivre-algorithms-deterministic-incremental-dependency-parsing/) - [READ–IT: Assessing Readability of Italian Texts with a View to Text Simplification](https://md.research.elamur.ai/free/en/papers/orletta-2011-read-it-assessing-readability-italian/) - [CoNLL-X Shared Task on Multilingual Dependency Parsing](https://md.research.elamur.ai/free/en/papers/parsers-2006-buchholz-conll-x-shared-task-multilingual/) - [Arc-swift: A Novel Transition System for Dependency Parsing](https://md.research.elamur.ai/free/en/papers/ud-2017-qi-arc-swift-novel-transition-system/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{attardi2006experiments, title = {{Experiments with a Multilanguage Non-Projective Dependency Parser}}, author = {Attardi, Giuseppe}, booktitle = {Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X)}, year = {2006}, doi = {10.3115/1596276.1596307}, url = {https://doi.org/10.3115/1596276.1596307} } ``` - [← previous Experiments on the Automatic Induction of German Semantic Verb Classes](https://md.research.elamur.ai/free/en/papers/walde-2006-experiments-automatic-induction-german-semantic/) - [next → Exploiting Semantic Role Labeling, WordNet and Wikipedia for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/ponzetto-2006-exploiting-semantic-role-labeling-wordnet/) - [↑ back to papers of 2006](https://md.research.elamur.ai/free/en/papers/2006/) ## References 13 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. A. Berger, S. Della Pietra, and M. Della Pietra. 1996. A Maximum Entropy Approach to Natural Language Processing. Computational Linguistics, 22(1). [find](https://scholar.google.com/scholar?q=A%2E+Berger%2C+S%2E+Della+Pietra%2C+and+M%2E+Della+Pietra%2E+1996%2E+A+Maximum+Entropy+Approach+to+Natural+Language+Processing%2E+Computational+Linguistics%2C+22%281%29%2E) [our card](https://md.research.elamur.ai/free/en/papers/berger-1996-maximum-entropy-approach-natural-language/) 2. S. Buchholz, et al. 2006. CoNLL-X Shared Task on Multilingual Dependency Parsing. In Proc. of the Tenth CoNLL. [find](https://scholar.google.com/scholar?q=S%2E+Buchholz%2C+et+al%2E+2006%2E+CoNLL%2DX+Shared+Task+on+Multilingual+Dependency+Parsing%2E+In+Proc%2E+of+the+Tenth+CoNLL%2E) [our card](https://md.research.elamur.ai/free/en/papers/parsers-2006-buchholz-conll-x-shared-task-multilingual/) 3. C.-C. Chang, C.-J. Lin. 2001. LIBSVM: a library for support vector machines. [http://www.csie.ntu.edu.tw/~cjlin/libsvm/](http://www.csie.ntu.edu.tw/~cjlin/libsvm/) [↗](http://www.csie.ntu.edu.tw/~cjlin/libsvm/) 4. W. Daelemans, J. Zavrel, K. van der Sloot, and A. van den Bosch. 2003. Timbl: Tilburg memory based learner, version 5.0, reference guide. Technical Report ILK 03-10, Tilburg University, ILK. [find](https://scholar.google.com/scholar?q=W%2E+Daelemans%2C+J%2E+Zavrel%2C+K%2E+van+der+Sloot%2C+and+A%2E+van+den+Bosch%2E+2003%2E+Timbl%3A+Tilburg+memory+based+learner%2C+version+5%2E0%2C+reference+guide%2E+Technical+Report+ILK+03%2D10%2C+Tilburg+University%2C+ILK%2E) 5. T. Kudo. 2002. tinySVM. [http://www.chasen.org/~taku/software/TinySVM/](http://www.chasen.org/~taku/software/TinySVM/) [↗](http://www.chasen.org/~taku/software/TinySVM/) 6. T. Kudo, Y. Matsumoto. 2002. Japanese Dependency Analysis using Cascaded Chunking. In Proc. of the Sixth CoNLL. [find](https://scholar.google.com/scholar?q=T%2E+Kudo%2C+Y%2E+Matsumoto%2E+2002%2E+Japanese+Dependency+Analysis+using+Cascaded+Chunking%2E+In+Proc%2E+of+the+Sixth+CoNLL%2E) 7. R. McDonald, et al. 2005. Non-projective Dependency Parsing using Spanning Tree Algorithms. In Proc. of HLT-EMNLP. [find](https://scholar.google.com/scholar?q=R%2E+McDonald%2C+et+al%2E+2005%2E+Non%2Dprojective+Dependency+Parsing+using+Spanning+Tree+Algorithms%2E+In+Proc%2E+of+HLT%2DEMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/narrative-2005-mcdonald-non-projective-dependency-parsing-spanning/) 8. J. Nivre, et al. 2004. Memory-based Dependency Parsing. In Proc.s of the Eighth CoNLL, ed. H. T. Ng and E. Riloff, Boston, Massachusetts, pp. 49–56. [find](https://scholar.google.com/scholar?q=J%2E+Nivre%2C+et+al%2E+2004%2E+Memory%2Dbased+Dependency+Parsing%2E+In+Proc%2Es+of+the+Eighth+CoNLL%2C+ed%2E+H%2E+T%2E+Ng+and+E%2E+Riloff%2C+Boston%2C+Massachusetts%2C+pp%2E+49%E2%80%9356%2E) [our card](https://md.research.elamur.ai/free/en/papers/nivre-2004-memory-based-dependency-parsing/) 9. J. Nivre and M. Scholz. 2004. Deterministic Dependency Parsing of English Text. In Proc. of COLING 2004, Geneva, Switzerland, pp. 64–70. [find](https://scholar.google.com/scholar?q=J%2E+Nivre+and+M%2E+Scholz%2E+2004%2E+Deterministic+Dependency+Parsing+of+English+Text%2E+In+Proc%2E+of+COLING+2004%2C+Geneva%2C+Switzerland%2C+pp%2E+64%E2%80%9370%2E) [our card](https://md.research.elamur.ai/free/en/papers/aclbulk-2004-nivre-deterministic-dependency-parsing-english-text/) 10. J. Nivre and J. Nilsson, 2005. Pseudo-Projective Dependency Parsing. In Proc. of the 43rd Annual Meeting of the ACL, pp. 99-106. [find](https://scholar.google.com/scholar?q=J%2E+Nivre+and+J%2E+Nilsson%2C+2005%2E+Pseudo%2DProjective+Dependency+Parsing%2E+In+Proc%2E+of+the+43rd+Annual+Meeting+of+the+ACL%2C+pp%2E+99%2D106%2E) 11. M.F. Porter. 2001. Snowball Stemmer. [http://www.snowball.tartarus.org/](http://www.snowball.tartarus.org/) [↗](http://www.snowball.tartarus.org/) 12. V. N. Vapnik. 1998. The Statistical Learning Theory. Springer. [find](https://scholar.google.com/scholar?q=V%2E+N%2E+Vapnik%2E+1998%2E+The+Statistical+Learning+Theory%2E+Springer%2E) 13. H. Yamada and Y. Matsumoto. 2003. Statistical Dependency Analysis with Support Vector Machines. In Proc. of the 8th International Workshop on Parsing Technologies (IWPT), pp. 195–206. [find](https://scholar.google.com/scholar?q=H%2E+Yamada+and+Y%2E+Matsumoto%2E+2003%2E+Statistical+Dependency+Analysis+with+Support+Vector+Machines%2E+In+Proc%2E+of+the+8th+International+Workshop+on+Parsing+Technologies+%28IWPT%29%2C+pp%2E+195%E2%80%93206%2E) [our card](https://md.research.elamur.ai/free/en/papers/parsers-2003-yamada-statistical-dependency-analysis-support-vector/)