--- title: "Data point selection for cross-language adaptation of" description: "This short ACL 2011 paper asks how to obtain a dependency parser for a language that has no… 10 references, cited by 74 papers here." authors: ["Anders Søgaard"] year: 2011 venue: "Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies" source: "https://aclanthology.org/P11-2120/" 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/sogaard-2011-data-point-selection-cross-language/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sogaard-2011-data-point-selection-cross-language/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2011](https://md.research.elamur.ai/free/en/papers/2011/) / Data point selection for cross-language adaptation of dependency parsers # Data point selection for cross-language adaptation of dependency parsers **Authors:** [Anders Søgaard](https://md.research.elamur.ai/free/en/authors/anders-sogaard/) · **Year:** 2011 · **Venue:** [Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2011](https://md.research.elamur.ai/free/en/venues/acl/2011/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/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/P11-2120/) · [PDF](https://aclanthology.org/P11-2120.pdf) · [OpenAlex](https://openalex.org/W4412272080) **Citations:** 5 citations (OpenAlex, 2026-10-14) · [74](https://md.research.elamur.ai/free/en/papers/sogaard-2011-data-point-selection-cross-language/cited-by/) in our library, of the 141,840 papers whose bibliographies we read ## Summary This short ACL 2011 paper asks how to obtain a dependency parser for a language that has no treebank of its own. The resources it relies on are labeled treebanks in other, possibly distant languages and unannotated target text. Søgaard extends the delexicalized transfer approach of Zeman and Resnik (2008). Source treebanks are stripped of words, and their POS tags are mapped to a shared tagset. A trigram language model is then trained on the target language's POS sequences. Each source sentence is scored by per-word perplexity under that model, and only the most target-like sentences are used to train the parser. The method is framed as a crude form of instance weighting under covariate shift, with binary weights. Experiments use the Arabic, Bulgarian, Danish and Portuguese treebanks from CoNLL 2006, a much less related set of languages than earlier work used. Dropping the least similar 10% of source sentences beats the unfiltered delexicalized baseline, sometimes by a wide margin. It also outperforms recent unsupervised parsers and roughly matches projection methods that need parallel text. ## Key points - **Setup:** - Four CoNLL 2006 treebanks with standard splits. - Tags unified via the Interset mappings used by Zeman and Resnik. - For each target language, the other three treebanks serve as the training material. - The parser is MSTParser (second-order, non-projective, MIRA) with default settings. - **Language model:** an unsmoothed trigram POS model built with SRILM. The author notes that modified Kneser-Ney smoothing does not apply to POS sequences. - **Full-length accuracy (baseline → 90% most similar):** - Bulgarian: 44.5 → 70.2 - Portuguese: 37.1 → 75.1 - Arabic: 45.5 → 48.4 - Danish: 51.7 → 51.9 - **Effect of the selection ratio:** - Choosing the ratio with 100 held-out sentences adds a little (e.g. Arabic 49.2, Danish 52.8). - Even 10% of the Bulgarian source data gives 66.9, well above the baseline. - **Single-source exploration:** using one source language can match or slightly beat the three-source setup. The best pairs were: - Portuguese from Bulgarian (76.9) - Bulgarian from Portuguese (70.3) - Danish from Arabic (56.5) - Arabic from Bulgarian (50.2) - **Weak Danish gains:** the author attributes these partly to the Danish treebank's unusual annotation, such as its DP-analysis of noun phrases. ## Interesting ideas - **Perplexity as a similarity filter:** a language model trained on unlabeled target data can rank labeled source examples by how target-like they are. This filtering idea could carry over to domain adaptation in tagging, NER or MT, where target labels are missing. - **Binary instance weights:** the importance weight P_t(x)/P_s(x) is reduced to keep-or-drop. This turns a theoretically motivated reweighting into a parameter-free data filter that wraps any learner without changing its internals. - **A sensible default ratio:** in this paper, discarding just the worst 10% gave most of the gain, and the exact amount kept mattered less. This makes a fixed default viable when no target dev data exists. - **Abstracting away the lexicon:** delexicalization plus a universal POS tagset lets structurally distant languages share training data. The pairwise experiments suggest checking non-obvious source languages rather than assuming that genealogical closeness is best. - **Error analysis by dependency length and root attachment:** breaking errors down this way reveals where an adaptation method actually helps. For Portuguese, the largest improvements came at the root and on long dependencies. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [University of Copenhagen](https://md.research.elamur.ai/free/en/universities/university-of-copenhagen/) — University, Copenhagen, Denmark · 78 works · 14,228 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works 🧭 Topics (2): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 465 works · [🌳 Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) · 120 works ## Cite Cite as: Anders Søgaard. 2011. Data point selection for cross-language adaptation of dependency parsers. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{sogaard2011data, title = {{Data point selection for cross-language adaptation of dependency parsers}}, author = {Anders Søgaard}, booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies}, year = {2011}, url = {https://aclanthology.org/P11-2120/} } ``` - [← previous Classifying Sentences as Speech Acts in Message Board Posts](https://md.research.elamur.ai/free/en/papers/qadir-2011-classifying-sentences-as-speech-acts/) - [next → Shallow Discourse Parsing with Conditional Random Fields](https://md.research.elamur.ai/free/en/papers/ghosh-2011-shallow-discourse-parsing-conditional-random/) - [↑ back to papers of 2011](https://md.research.elamur.ai/free/en/papers/2011/) ## References 10 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Kuzman Ganchev, Jennifer Gillenwater, and Ben Taskar. 2009. [Dependency grammar induction via bitext projection constraints](https://md.research.elamur.ai/free/en/papers/ganchev-2009-dependency-grammar-induction-bitext-projection/). In ACL. 2. Jennifer Gillenwater, Kuzman Ganchev, Joao Graca, Fernando Pereira, and Ben Taskar. 2010. Sparsity in dependency grammar induction. In ACL. [find](https://scholar.google.com/scholar?q=Jennifer+Gillenwater%2C+Kuzman+Ganchev%2C+Joao+Graca%2C+Fernando+Pereira%2C+and+Ben+Taskar%2E+2010%2E+Sparsity+in+dependency+grammar+induction%2E+In+ACL%2E) 3. Dan Klein and Christopher Manning. 2004. Corpus-based induction of syntactic structure: models of dependency and constituency. In ACL. [find](https://scholar.google.com/scholar?q=Dan+Klein+and+Christopher+Manning%2E+2004%2E+Corpus%2Dbased+induction+of+syntactic+structure%3A+models+of+dependency+and+constituency%2E+In+ACL%2E) 4. Ryan McDonald, Koby Crammer, and Fernando Pereira. 2005. [Online large-margin training of dependency parsers](https://md.research.elamur.ai/free/en/papers/mcdonald-2005-online-large-margin-training-dependency/). In ACL. 5. Tahira Naseem, Harr Chen, Regina Barzilay, and Mark Johnson. 2010. [Using universal linguistic knowledge to guide grammar induction](https://md.research.elamur.ai/free/en/papers/naseem-2010-universal-linguistic-knowledge-guide-grammar/). In EMNLP. 6. Hidetoshi Shimodaira. 2000. Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 90:227–244. [find](https://scholar.google.com/scholar?q=Hidetoshi+Shimodaira%2E+2000%2E+Improving+predictive+inference+under+covariate+shift+by+weighting+the+log%2Dlikelihood+function%2E+Journal+of+Statistical+Planning+and+Inference%2C+90%3A227%E2%80%93244%2E) 7. David Smith and Jason Eisner. 2009. Parser adaptation and projection with quasi-synchronous grammar features. In EMNLP. [find](https://scholar.google.com/scholar?q=David+Smith+and+Jason+Eisner%2E+2009%2E+Parser+adaptation+and+projection+with+quasi%2Dsynchronous+grammar+features%2E+In+EMNLP%2E) 8. Kathrin Spreyer and Jonas Kuhn. 2009. Data-driven dependency parsing of new languages using incomplete and noisy training data. In CoNLL. [find](https://scholar.google.com/scholar?q=Kathrin+Spreyer+and+Jonas+Kuhn%2E+2009%2E+Data%2Ddriven+dependency+parsing+of+new+languages+using+incomplete+and+noisy+training+data%2E+In+CoNLL%2E) 9. Kathrin Spreyer, Lilja Øvrelid, and Jonas Kuhn. 2010. Training parsers on partial trees: a cross-language comparison. In LREC. [find](https://scholar.google.com/scholar?q=Kathrin+Spreyer%2C+Lilja+%C3%98vrelid%2C+and+Jonas+Kuhn%2E+2010%2E+Training+parsers+on+partial+trees%3A+a+cross%2Dlanguage+comparison%2E+In+LREC%2E) 10. Daniel Zeman and Philip Resnik. 2008. [Cross-language parser adaptation between related languages](https://md.research.elamur.ai/free/en/papers/zeman-2008-cross-language-parser-adaptation-between/). In IJC-NLP. *Updated 24 October 2026*