--- title: "Multilingual Projection for Parsing Truly — Agić 2016" description: "Most cross-lingual methods for POS tagging and dependency parsing were built and tested on Germanic and Romance languages." authors: ["Željko Agić", "Anders Johannsen", "Barbara Plank", "Héctor Martínez Alonso", "Natalie Schluter", "Anders Søgaard"] year: 2016 venue: "Transactions of the Association for Computational Linguistics" source: "https://aclanthology.org/Q16-1022/" doi: "10.1162/tacl_a_00100" 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/agic-2016-multilingual-projection-parsing-truly-low/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/agic-2016-multilingual-projection-parsing-truly-low/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/3/) / Multilingual Projection for Parsing Truly Low-Resource Languages # Multilingual Projection for Parsing Truly Low-Resource Languages **Authors:** [Željko Agić](https://md.research.elamur.ai/free/en/authors/zeljko-agic/), [Anders Johannsen](https://md.research.elamur.ai/free/en/authors/anders-johannsen/), [Barbara Plank](https://md.research.elamur.ai/free/en/authors/barbara-plank/), [Héctor Martínez Alonso](https://md.research.elamur.ai/free/en/authors/hector-martinez-alonso/), [Natalie Schluter](https://md.research.elamur.ai/free/en/authors/natalie-schluter/), [Anders Søgaard](https://md.research.elamur.ai/free/en/authors/anders-sogaard/) · **Year:** 2016 · **Venue:** Transactions of the Association for Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/Q16-1022/) · [PDF](https://aclanthology.org/Q16-1022.pdf) · [DOI 10.1162/tacl\_a\_00100](https://doi.org/10.1162/tacl_a_00100) · [OpenAlex](https://openalex.org/W2494423583) **Citations:** 116 citations (openalex-snapshot · 2026-10-14) · [79](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Most cross-lingual methods for POS tagging and dependency parsing were built and tested on Germanic and Romance languages. These languages have abundant parallel data, easy tokenization and similar word order, so such work may overstate what is achievable for truly low-resource languages. Agić et al. assume nothing about the target language except a translated text. They use the Bible (EBC) and Watchtower publications (WTC), which are massively multi-parallel, together with taggers and parsers for resource-rich source languages. POS tags are transferred by alignment-weighted voting across many source languages. For syntax, they propose a heuristics-free projection. Rather than projecting a single best tree from one source, they carry each source parser's standardized scores for every candidate edge through the word alignments and sum them over all sources. Only the combined target matrix is then decoded into a tree. They built models for more than 100 languages and evaluated them on 30 languages with test data. The method outperforms delexicalized transfer and standard projection heuristics, with particularly strong results on non-Indo-European languages. This makes basic syntactic tools feasible for languages without any annotated data. ## Key points - Parallel sources: Bible excerpts exist in 1,646 languages and Watchtower texts in up to 583. No tag dictionaries, labeled data or typological information are used for target languages. - The dependency projection transfers dense edge-weight matrices from multiple sources and delays tree decoding (maximum spanning tree) until after aggregation. Weights are normalized per sentence. - Taggers and parsers were trained for over 100 languages and evaluated on 30 test languages. Training was capped at 20k sentences per language, although EBC/WTC offer up to 120k, because adding more data gave little benefit. - Parsers rely on projected (noisy) POS tags, yet about 40% of tokens with wrong POS predictions still receive the correct syntactic head. - Code and data are released at bitbucket.org/lowlands/release. The work was funded by the ERC Starting Grant LOWLANDS. *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/) Topics: [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) ## Cited by Cited by 79 papers of our library cite it (of the 140884 whose bibliographies we read); 8 of them have a page here, 71 not yet. - [Cross-Lingual Parser Selection for Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/agic-2017-cross-lingual-parser-selection-low/) - [JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/agic-2019-jw300-wide-coverage-parallel-corpus/) - [A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing](https://md.research.elamur.ai/free/en/papers/anderson-2021-falta-de-pan-buenas-son/) - [Parsing in the absence of related languages: Evaluating low-resource dependency parsers on Tagalog](https://md.research.elamur.ai/free/en/papers/aquino-2020-parsing-absence-related-languages-evaluating/) - [Improving Cross-lingual Transfer through Subtree-aware Word Reordering](https://md.research.elamur.ai/free/en/papers/arviv-2023-improving-cross-lingual-transfer-through/) - [Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP](https://md.research.elamur.ai/free/en/papers/goot-2021-massive-choice-ample-tasks-machamp/) - [Dependency Parsing Evaluation for Low-resource Spontaneous Speech](https://md.research.elamur.ai/free/en/papers/ud-2021-liu-dependency-parsing-evaluation-low-resource/) - [Producing a Parallel Universal Dependencies Treebank of Ancient Hebrew and Ancient Greek via Cross-Lingual Projection](https://md.research.elamur.ai/free/en/papers/ud-2024-swanson-producing-parallel-universal-dependencies-treebank/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @article{agic2016multilingual, title = {{Multilingual Projection for Parsing Truly Low-Resource Languages}}, author = {Agić, Željko and Johannsen, Anders and Plank, Barbara and Alonso, Héctor Martínez and Schluter, Natalie and Søgaard, Anders}, journal = {Transactions of the Association for Computational Linguistics}, year = {2016}, doi = {10.1162/tacl\_a\_00100}, url = {https://doi.org/10.1162/tacl_a_00100} } ``` - [← previous Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss](https://md.research.elamur.ai/free/en/papers/plank-2016-multilingual-part-speech-tagging-bidirectional/) - [next → Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding](https://md.research.elamur.ai/free/en/papers/fukui-2016-multimodal-compact-bilinear-pooling-visual/) - [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/3/) ## References 17 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Željko Agić, Dirk Hovy, and Anders Søgaard. 2015. If All You Have is a Bit of the Bible: Learning POS Taggers for Truly Low-Resource Languages. In ACL. [find](https://scholar.google.com/scholar?q=Z%CC%8Celjko+Agic%CC%81%2C+Dirk+Hovy%2C+and+Anders+S%C3%B8gaard%2E+2015%2E+If+All+You+Have+is+a+Bit+of+the+Bible%3A+Learning+POS+Taggers+for+Truly+Low%2DResource+Languages%2E+In+ACL%2E) 2. TnT: A Statistical Part-of-Speech Tagger. In ANLP. Christos Christodouloupoulos and Mark Steedman. 2014. A Massively Parallel Corpus: The Bible in 100 Languages. Language Resources and Evaluation, 49(2). [find](https://scholar.google.com/scholar?q=TnT%3A+A+Statistical+Part%2Dof%2DSpeech+Tagger%2E+In+ANLP%2E+Christos+Christodouloupoulos+and+Mark+Steedman%2E+2014%2E+A+Massively+Parallel+Corpus%3A+The+Bible+in+100+Languages%2E+Language+Resources+and+Evaluation%2C+49%28) [our card](https://md.research.elamur.ai/free/en/papers/christodouloupoulos-2014-massively-parallel-corpus-bible-100/) 3. Dipanjan Das and Slav Petrov. 2011. Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections. In ACL. [find](https://scholar.google.com/scholar?q=Dipanjan+Das+and+Slav+Petrov%2E+2011%2E+Unsupervised+Part%2Dof%2DSpeech+Tagging+with+Bilingual+Graph%2DBased+Projections%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/das-2011-unsupervised-part-speech-tagging-bilingual/) 4. Chris Dyer, Victor Chahuneau, and Noah A. Smith. 2013. A Simple, Fast, and Effective Reparameterization of IBM Model 2. In ACL. [find](https://scholar.google.com/scholar?q=Chris+Dyer%2C+Victor+Chahuneau%2C+and+Noah+A%2E+Smith%2E+2013%2E+A+Simple%2C+Fast%2C+and+Effective+Reparameterization+of+IBM+Model+2%2E+In+ACL%2E) 5. Dan Garrette, Jason Mielens, and Jason Baldridge. 2013. Real-World Semi-Supervised Learning of POS-Taggers for Low-Resource Languages. In ACL. [find](https://scholar.google.com/scholar?q=Dan+Garrette%2C+Jason+Mielens%2C+and+Jason+Baldridge%2E+2013%2E+Real%2DWorld+Semi%2DSupervised+Learning+of+POS%2DTaggers+for+Low%2DResource+Languages%2E+In+ACL%2E) 6. Rebecca Hwa, Philip Resnik, Amy Weinberg, Clara Cabezas, and Okan Kolak. 2005. Bootstrapping Parsers via Syntactic Projection Across Parallel Texts. Natural Language Engineering, 11(3). Anders Johannsen, Željko Agić, and Anders Søgaard. 2016. Joint Part-of-Speech and Dependency Projection from Mul… [find](https://scholar.google.com/scholar?q=Rebecca+Hwa%2C+Philip+Resnik%2C+Amy+Weinberg%2C+Clara+Cabezas%2C+and+Okan+Kolak%2E+2005%2E+Bootstrapping+Parsers+via+Syntactic+Projection+Across+Parallel+Texts%2E+Natural+Language+Engineering%2C+11%283%29%2E+Anders+Johanns) 7. Wiki-ly Supervised Part-of-Speech Tagging. In EMNLP. Zhenghua Li, Min Zhang, and Wenliang Chen. 2014. Soft Cross-lingual Syntax Projection for Dependency Parsing. In COLING. [find](https://scholar.google.com/scholar?q=Wiki%2Dly+Supervised+Part%2Dof%2DSpeech+Tagging%2E+In+EMNLP%2E+Zhenghua+Li%2C+Min+Zhang%2C+and+Wenliang+Chen%2E+2014%2E+Soft+Cross%2Dlingual+Syntax+Projection+for+Dependency+Parsing%2E+In+COLING%2E) 8. Xuezhe Ma and Fei Xia. 2014. Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization. In ACL. André F. T. Martins, Miguel Almeida, and Noah A. Smith. 2013. Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers. In ACL. [find](https://scholar.google.com/scholar?q=Xuezhe+Ma+and+Fei+Xia%2E+2014%2E+Unsupervised+Dependency+Parsing+with+Transferring+Distribution+via+Parallel+Guidance+and+Entropy+Regularization%2E+In+ACL%2E+Andre%CC%81+F%2E+T%2E+Martins%2C+Miguel+Almeida%2C+and+Noah+A%2E+) 9. Ryan McDonald, Koby Crammer, and Fernando Pereira. 2005. Online Large-Margin Training of Dependency Parsers. In ACL. [find](https://scholar.google.com/scholar?q=Ryan+McDonald%2C+Koby+Crammer%2C+and+Fernando+Pereira%2E+2005%2E+Online+Large%2DMargin+Training+of+Dependency+Parsers%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/narrative-2005-mcdonald-online-large-margin-training-dependency/) 10. Ryan McDonald, Slav Petrov, and Keith Hall. 2011. Multi-Source Transfer of Delexicalized Dependency Parsers. In EMNLP. Ryan McDonald, Joakim Nivre, Yvonne Quirmbach-Brundage, Yoav Goldberg, Dipanjan Das, Kuzman Ganchev, Keith Hall, Slav Petrov, Hao Zhang, Oscar Täckström, Claudia Bedini, Núria Be… [find](https://scholar.google.com/scholar?q=Ryan+McDonald%2C+Slav+Petrov%2C+and+Keith+Hall%2E+2011%2E+Multi%2DSource+Transfer+of+Delexicalized+Dependency+Parsers%2E+In+EMNLP%2E+Ryan+McDonald%2C+Joakim+Nivre%2C+Yvonne+Quirmbach%2DBrundage%2C+Yoav+Goldberg%2C+Dipanjan+D) [our card](https://md.research.elamur.ai/free/en/papers/mcdonald-2011-multi-source-transfer-delexicalized-dependency/) 11. Word Order Typology Through Multilingual Word Alignment. In ACL. Slav Petrov, Dipanjan Das, and Ryan McDonald. 2012. [find](https://scholar.google.com/scholar?q=Word+Order+Typology+Through+Multilingual+Word+Alignment%2E+In+ACL%2E+Slav+Petrov%2C+Dipanjan+Das%2C+and+Ryan+McDonald%2E+2012%2E) 12. A Universal Part-of-Speech Tagset. In LREC. Mohammad Sadegh Rasooli and Michael Collins. 2015. Density-Driven Cross-Lingual Transfer of Dependency Parsers. In EMNLP. Rudolf Rosa and Zdeněk Žabokrtský. 2015. KLcpos3: A Language Similarity Measure for Delexicalized Parser Transfer. In ACL. [find](https://scholar.google.com/scholar?q=A+Universal+Part%2Dof%2DSpeech+Tagset%2E+In+LREC%2E+Mohammad+Sadegh+Rasooli+and+Michael+Collins%2E+2015%2E+Density%2DDriven+Cross%2DLingual+Transfer+of+Dependency+Parsers%2E+In+EMNLP%2E+Rudolf+Rosa+and+Zdene%CC%8Ck+Z%CC%8Cabokrtsk) 13. Kenji Sagae and Alon Lavie. 2006. Parser Combination by Reparsing. In NAACL. [find](https://scholar.google.com/scholar?q=Kenji+Sagae+and+Alon+Lavie%2E+2006%2E+Parser+Combination+by+Reparsing%2E+In+NAACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/sagae-2006-parser-combination-reparsing/) 14. 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) 15. Anders Søgaard. 2011. Data Point Selection for Cross-Language Adaptation of Dependency Parsers. In ACL. Jörg Tiedemann and Željko Agić. 2016. Synthetic Treebanking for Cross-Lingual Dependency Parsing. Journal of Artificial Intelligence Research, 55. Jörg Tiedemann, Željko Agić, and Joakim Niv… [find](https://scholar.google.com/scholar?q=Anders+S%C3%B8gaard%2E+2011%2E+Data+Point+Selection+for+Cross%2DLanguage+Adaptation+of+Dependency+Parsers%2E+In+ACL%2E+Jo%CC%88rg+Tiedemann+and+Z%CC%8Celjko+Agic%CC%81%2E+2016%2E+Synthetic+Treebanking+for+Cross%2DLingual+Dependency+Pars) 16. David Yarowsky, Grace Ngai, and Richard Wicentowski. 2001. Inducing Multilingual Text Analysis Tools via Robust Projection Across Aligned Corpora. In NAACL. [find](https://scholar.google.com/scholar?q=David+Yarowsky%2C+Grace+Ngai%2C+and+Richard+Wicentowski%2E+2001%2E+Inducing+Multilingual+Text+Analysis+Tools+via+Robust+Projection+Across+Aligned+Corpora%2E+In+NAACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/yarowsky-2001-inducing-multilingual-text-analysis-tools/) 17. Daniel Zeman and Philip Resnik. 2008. Cross-Language Parser Adaptation Between Related Languages. In IJCNLP Workshop on NLP for Less Privileged Languages. [find](https://scholar.google.com/scholar?q=Daniel+Zeman+and+Philip+Resnik%2E+2008%2E+Cross%2DLanguage+Parser+Adaptation+Between+Related+Languages%2E+In+IJCNLP+Workshop+on+NLP+for+Less+Privileged+Languages%2E) [our card](https://md.research.elamur.ai/free/en/papers/zeman-2008-cross-language-parser-adaptation-between/)