---
title: "Cross-Lingual Parser Selection for Low-Resource — Agić 2017"
description: "Delexicalized parsers operate only on sequences of universal POS tags."
authors: ["Željko Agić"]
year: 2017
venue: "Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017)"
source: "https://aclanthology.org/W17-0401/"
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/papers/agic-2017-cross-lingual-parser-selection-low/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/agic-2017-cross-lingual-parser-selection-low/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2017](https://md.research.elamur.ai/free/papers/2017/) / Cross-Lingual Parser Selection for Low-Resource Languages

# Cross-Lingual Parser Selection for Low-Resource Languages

**Authors:** [Željko Agić](https://md.research.elamur.ai/free/authors/zeljko-agic/) · **Year:** 2017 · **Venue:** Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/W17-0401/) · [PDF](https://aclanthology.org/W17-0401.pdf) · [OpenAlex](https://openalex.org/W2610714671)

**Citations:** 23 citations (openalex-snapshot · 2026-10-14) · [23](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Delexicalized parsers operate only on sequences of universal POS tags. They can therefore be used to analyze the syntactic dependencies of almost any language. The question remains which source-language model to apply to a given text. Usually the best parser is selected based on results on the target-language test data. In essence, this is an oracle that is not available in real-world conditions. The author proposes a lightweight method for selecting the source at system run time. The language of the input text is identified automatically, and its proximity to the source languages is estimated with three measures: the divergence of POS-trigram distributions (KL-POS), the probability from the langid.py language identifier (LANG-ID), and the similarity of typological features in the WALS database. These measures are combined linearly, and the parses of all parsers are merged via reparsing (maximum spanning tree). The experiments cover 26 languages from UD. Cross-lingual POS taggers are used, and the input size varies down to a single sentence. The combined system consistently finds suitable parsers and even outperforms the oracle single-best. The work shows how important a realistic experimental design is for truly low-resource languages.

## Key points
- Three distance measures:
  - KL-POS: the metric of Rosa and Žabokrtský (2015), but with linear interpolation smoothing following Brants (2000).
  - LANG-ID: langid.py, a naive Bayes classifier over byte n-grams (1–4), with pretrained models for ~100 languages.
  - WALS: Hamming distance between feature vectors; the database contains 2 679 languages and 202 features.
- Example with a single Croatian sentence: KL-POS selects the Finnish parser (19th of 26), while with five sentences it already selects the Slovenian one (1st). LANG-ID and WALS select Slovenian already for a single sentence.
- The test-set-level single-best oracle achieves a UAS of 51.96±4.35. If the best source were chosen separately for each sentence, UAS would rise to 65.54 (+13.58). In 28.66% of sentences, the best parse is produced by a parser other than the one ranked first overall.
- Limitations: tokenization and sentence segmentation are taken from the gold annotation. The cross-lingual taggers of Agić et al. (2016) are not selected at run time but are used as data.
- Code and data are openly available: the freasy repository on Bitbucket.

*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/shelves/linguistics/)

Topics: [Part-of-speech tagging](https://md.research.elamur.ai/free/topics/part-of-speech-tagging/)

## Cited by

Cited by

23 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 19 not yet.

- [Parsing in the absence of related languages: Evaluating low-resource dependency parsers on Tagalog](https://md.research.elamur.ai/free/papers/aquino-2020-parsing-absence-related-languages-evaluating/)
- [The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project](https://md.research.elamur.ai/free/papers/aquino-2025-ud-newscrawl-treebank-reflections-challenges/)
- [Universal Dependencies](https://md.research.elamur.ai/free/papers/demarneffe-2021-universal-dependencies/)
- [Challenges and Strategies in Cross-Cultural NLP](https://md.research.elamur.ai/free/papers/hershcovich-2022-challenges-strategies-cross-cultural-nlp/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{agic2017cross,
  title = {{Cross-Lingual Parser Selection for Low-Resource Languages}},
  author = {Agić, Željko},
  booktitle = {Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017)},
  year = {2017},
  url = {https://aclanthology.org/W17-0401/}
}
```

- [← previous Creating Training Corpora for NLG Micro-Planners](https://md.research.elamur.ai/free/papers/gardent-2017-creating-training-corpora-nlg-micro/)
- [next → Cross-lingual RST Discourse Parsing](https://md.research.elamur.ai/free/papers/braud-2017-cross-lingual-rst-discourse-parsing/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/papers/2017/)

## References

31 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, pages 268–272. [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%2C+pages+268%E2%80%93272%2E)
2. Plank and Van Noord (2011) applied similarity measures over cross-domain data for dependency Tahira Naseem, Regina Barzilay, and Amir Globerson. 2012. Selective Sharing for Multilingual Dependency Parsing. In ACL, pages 629–637. [find](https://scholar.google.com/scholar?q=Plank+and+Van+Noord+%282011%29+applied+similarity+measures+over+cross%2Ddomain+data+for+dependency+Tahira+Naseem%2C+Regina+Barzilay%2C+and+Amir+Globerson%2E+2012%2E+Selective+Sharing+for+Multilingual+Dependency+Par)
3. Željko Agić, Anders Johannsen, Barbara Plank, Héctor Martı́nez Alonso, Natalie Schluter, and Anders Søgaard. 2016. Multilingual Projection for Parsing Truly Low-Resource Languages. TACL, 4:301–312. [find](https://scholar.google.com/scholar?q=Z%CC%8Celjko+Agic%CC%81%2C+Anders+Johannsen%2C+Barbara+Plank%2C+He%CC%81ctor+Mart%C4%B1%CC%81nez+Alonso%2C+Natalie+Schluter%2C+and+Anders+S%C3%B8gaard%2E+2016%2E+Multilingual+Projection+for+Parsing+Truly+Low%2DResource+Languages%2E+TACL%2C+4%3A301%E2%80%93312%2E)
4. Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Yoav Goldberg, Jan Hajič, Christopher D Manning, Ryan McDonald, Slav Petrov, Sampo Pyysalo, Natalia Silveira, et al. 2016. Universal Dependencies v1: A Multilingual Treebank Collection. In LREC 2016, pages 1659–1666. [find](https://scholar.google.com/scholar?q=Joakim+Nivre%2C+Marie%2DCatherine+de+Marneffe%2C+Filip+Ginter%2C+Yoav+Goldberg%2C+Jan+Hajic%CC%8C%2C+Christopher+D+Manning%2C+Ryan+McDonald%2C+Slav+Petrov%2C+Sampo+Pyysalo%2C+Natalia+Silveira%2C+et+al%2E+2016%2E+Universal+Dependenc) [our card](https://md.research.elamur.ai/free/papers/ud-2016-nivre-universal-dependencies-v1-multilingual-treebank/)
5. Waleed Ammar, George Mulcaire, Miguel Ballesteros, Chris Dyer, and Noah A. Smith. 2016. Many Languages, One Parser. TACL, pages 431–444. [find](https://scholar.google.com/scholar?q=Waleed+Ammar%2C+George+Mulcaire%2C+Miguel+Ballesteros%2C+Chris+Dyer%2C+and+Noah+A%2E+Smith%2E+2016%2E+Many+Languages%2C+One+Parser%2E+TACL%2C+pages+431%E2%80%93444%2E) [our card](https://md.research.elamur.ai/free/papers/ammar-2016-many-languages-one-parser/)
6. Bernd Bohnet. 2010. Very High Accuracy and Fast Dependency Parsing is not a Contradiction. In COL-ING, pages 89–97. [find](https://scholar.google.com/scholar?q=Bernd+Bohnet%2E+2010%2E+Very+High+Accuracy+and+Fast+Dependency+Parsing+is+not+a+Contradiction%2E+In+COL%2DING%2C+pages+89%E2%80%9397%2E) [our card](https://md.research.elamur.ai/free/papers/bohnet-2010-top-accuracy-fast-dependency-parsing/)
7. Thorsten Brants. 2000. TnT: A Statistical Part-of-Speech Tagger. In ANLP, pages 224–231. [find](https://scholar.google.com/scholar?q=Thorsten+Brants%2E+2000%2E+TnT%3A+A+Statistical+Part%2Dof%2DSpeech+Tagger%2E+In+ANLP%2C+pages+224%E2%80%93231%2E) [our card](https://md.research.elamur.ai/free/papers/brants-2000-tnt-statistical-part-speech-tagger/)
8. Helen O’Horan, Yevgeni Berzak, Ivan Vulić, Roi Reichart, and Anna Korhonen. 2016. Survey on the Use of Typological Information in Natural Language Processing. arXiv preprint arXiv:1610.03349. [find](https://scholar.google.com/scholar?q=Helen+O%E2%80%99Horan%2C+Yevgeni+Berzak%2C+Ivan+Vulic%CC%81%2C+Roi+Reichart%2C+and+Anna+Korhonen%2E+2016%2E+Survey+on+the+Use+of+Typological+Information+in+Natural+Language+Processing%2E+arXiv+preprint+arXiv%3A1610%2E03349%2E)
9. Dipanjan Das and Slav Petrov. 2011. Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections. In ACL, pages 600–609. [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%2C+pages+600%E2%80%93609%2E)
10. Robert Östling. 2015. Word Order Typology Through Multilingual Word Alignment. In ACL, pages 205– 211. [find](https://scholar.google.com/scholar?q=Robert+O%CC%88stling%2E+2015%2E+Word+Order+Typology+Through+Multilingual+Word+Alignment%2E+In+ACL%2C+pages+205%E2%80%93+211%2E)
11. Slav Petrov, Dipanjan Das, and Ryan McDonald. 2011. A Universal Part-of-Speech Tagset. arXiv preprint arXiv:1104.2086. [find](https://scholar.google.com/scholar?q=Slav+Petrov%2C+Dipanjan+Das%2C+and+Ryan+McDonald%2E+2011%2E+A+Universal+Part%2Dof%2DSpeech+Tagset%2E+arXiv+preprint+arXiv%3A1104%2E2086%2E)
12. Matthew S. Dryer and Martin Haspelmath, editors. 2013. The World Atlas of Language Structures Online. Max Planck Institute for Evolutionary Anthropology, Leipzig. [find](https://scholar.google.com/scholar?q=Matthew+S%2E+Dryer+and+Martin+Haspelmath%2C+editors%2E+2013%2E+The+World+Atlas+of+Language+Structures+Online%2E+Max+Planck+Institute+for+Evolutionary+Anthropology%2C+Leipzig%2E)
13. Barbara Plank and Gertjan Van Noord. 2011. Effective Measures of Domain Similarity for Parsing. In ACL, pages 1566–1576. [find](https://scholar.google.com/scholar?q=Barbara+Plank+and+Gertjan+Van+Noord%2E+2011%2E+Effective+Measures+of+Domain+Similarity+for+Parsing%2E+In+ACL%2C+pages+1566%E2%80%931576%2E)
14. Ryan Georgi, Fei Xia, and William Lewis. 2010. Comparing Language Similarity Across Genetic and Typologically-Based Groupings. In COLING, pages 385–393. [find](https://scholar.google.com/scholar?q=Ryan+Georgi%2C+Fei+Xia%2C+and+William+Lewis%2E+2010%2E+Comparing+Language+Similarity+Across+Genetic+and+Typologically%2DBased+Groupings%2E+In+COLING%2C+pages+385%E2%80%93393%2E)
15. Taraka Rama and Prasanth Kolachina. 2012. How Good are Typological Distances for Determining Genealogical Relationships among Languages? In COLING, pages 975–984. [find](https://scholar.google.com/scholar?q=Taraka+Rama+and+Prasanth+Kolachina%2E+2012%2E+How+Good+are+Typological+Distances+for+Determining+Genealogical+Relationships+among+Languages%3F+In+COLING%2C+pages+975%E2%80%93984%2E)
16. Jan Hajič, Massimiliano Ciaramita, Richard Johansson, Daisuke Kawahara, Maria Antònia Martı́, Lluı́s Màrquez, Adam Meyers, Joakim Nivre, Sebastian Padó, Jan Štěpánek, et al. 2009. The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages. In CoNLL, pages 1–18. [find](https://scholar.google.com/scholar?q=Jan+Hajic%CC%8C%2C+Massimiliano+Ciaramita%2C+Richard+Johansson%2C+Daisuke+Kawahara%2C+Maria+Anto%CC%80nia+Mart%C4%B1%CC%81%2C+Llu%C4%B1%CC%81s+Ma%CC%80rquez%2C+Adam+Meyers%2C+Joakim+Nivre%2C+Sebastian+Pado%CC%81%2C+Jan+S%CC%8Cte%CC%8Cpa%CC%81nek%2C+et+al%2E+2009%2E+The+CoNLL%2D200) [our card](https://md.research.elamur.ai/free/papers/hajic-2009-conll-2009-shared-task-syntactic/)
17. Mohammad Sadegh Rasooli and Michael Collins. 2015. Density-Driven Cross-Lingual Transfer of Dependency Parsers. In EMNLP, pages 328–338. [find](https://scholar.google.com/scholar?q=Mohammad+Sadegh+Rasooli+and+Michael+Collins%2E+2015%2E+Density%2DDriven+Cross%2DLingual+Transfer+of+Dependency+Parsers%2E+In+EMNLP%2C+pages+328%E2%80%93338%2E)
18. Rudolf Rosa and Zdeněk Žabokrtský. 2015a. KLcpos3 - a Language Similarity Measure for Delexicalized Parser Transfer. In ACL, pages 243–249. [find](https://scholar.google.com/scholar?q=Rudolf+Rosa+and+Zdene%CC%8Ck+Z%CC%8Cabokrtsky%CC%81%2E+2015a%2E+KLcpos3+%2D+a+Language+Similarity+Measure+for+Delexicalized+Parser+Transfer%2E+In+ACL%2C+pages+243%E2%80%93249%2E)
19. Anders Johannsen, Željko Agić, and Anders Søgaard. 2016. Joint Part-of-Speech and Dependency Projection from Multiple Sources. In ACL, pages 561–566. [find](https://scholar.google.com/scholar?q=Anders+Johannsen%2C+Z%CC%8Celjko+Agic%CC%81%2C+and+Anders+S%C3%B8gaard%2E+2016%2E+Joint+Part%2Dof%2DSpeech+and+Dependency+Projection+from+Multiple+Sources%2E+In+ACL%2C+pages+561%E2%80%93566%2E)
20. Rudolf Rosa and Zdeněk Žabokrtský. 2015b. MST-Parser Model Interpolation for Multi-source Delexicalized Transfer. In IWPT, pages 71–75. [find](https://scholar.google.com/scholar?q=Rudolf+Rosa+and+Zdene%CC%8Ck+Z%CC%8Cabokrtsky%CC%81%2E+2015b%2E+MST%2DParser+Model+Interpolation+for+Multi%2Dsource+Delexicalized+Transfer%2E+In+IWPT%2C+pages+71%E2%80%9375%2E)
21. Marco Lui and Timothy Baldwin. 2012. langid.py: An Off-the-Shelf Language Identification Tool. In ACL, pages 25–30. [find](https://scholar.google.com/scholar?q=Marco+Lui+and+Timothy+Baldwin%2E+2012%2E+langid%2Epy%3A+An+Off%2Dthe%2DShelf+Language+Identification+Tool%2E+In+ACL%2C+pages+25%E2%80%9330%2E) [our card](https://md.research.elamur.ai/free/papers/lui-2012-langid-py-off-shelf-language/)
22. Kenji Sagae and Alon Lavie. 2006. Parser Combination by Reparsing. In NAACL, pages 129–132. [find](https://scholar.google.com/scholar?q=Kenji+Sagae+and+Alon+Lavie%2E+2006%2E+Parser+Combination+by+Reparsing%2E+In+NAACL%2C+pages+129%E2%80%93132%2E)
23. Xuezhe Ma and Fei Xia. 2014. Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization. In ACL, pages 1337–1348. [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%2C+pages+1337%E2%80%931348%2E)
24. Anders Søgaard and Julie Wulff. 2012. An Empirical Study of Non-Lexical Extensions to Delexicalized Transfer. In COLING, pages 1181–1190. [find](https://scholar.google.com/scholar?q=Anders+S%C3%B8gaard+and+Julie+Wulff%2E+2012%2E+An+Empirical+Study+of+Non%2DLexical+Extensions+to+Delexicalized+Transfer%2E+In+COLING%2C+pages+1181%E2%80%931190%2E)
25. Ryan McDonald, Slav Petrov, and Keith Hall. 2011. Multi-Source Transfer of Delexicalized Dependency Parsers. In EMNLP, pages 62–72. [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%2C+pages+62%E2%80%9372%2E) [our card](https://md.research.elamur.ai/free/papers/mcdonald-2011-multi-source-transfer-delexicalized-dependency/)
26. Anders Søgaard. 2011. Data Point Selection for Cross-Language Adaptation of Dependency Parsers. In ACL, pages 682–686. [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%2C+pages+682%E2%80%93686%2E)
27. Ryan McDonald, Joakim Nivre, Yvonne Quirmbach-Brundage, Yoav Goldberg, Dipanjan Das, Kuzman Ganchev, Keith Hall, Slav Petrov, Hao Zhang, Oscar Täckström, Claudia Bedini, Núria Bertomeu Castelló, and Jungmee Lee. 2013. Universal Dependency Annotation for Multilingual Parsing. In ACL, pages 92–97. [find](https://scholar.google.com/scholar?q=Ryan+McDonald%2C+Joakim+Nivre%2C+Yvonne+Quirmbach%2DBrundage%2C+Yoav+Goldberg%2C+Dipanjan+Das%2C+Kuzman+Ganchev%2C+Keith+Hall%2C+Slav+Petrov%2C+Hao+Zhang%2C+Oscar+Ta%CC%88ckstro%CC%88m%2C+Claudia+Bedini%2C+Nu%CC%81ria+Bertomeu+Castello%CC%81%2C+a)
28. Oscar Täckström, Ryan McDonald, and Joakim Nivre. 2013. Target Language Adaptation of Discriminative Transfer Parsers. In NAACL, pages 1061–1071. [find](https://scholar.google.com/scholar?q=Oscar+Ta%CC%88ckstro%CC%88m%2C+Ryan+McDonald%2C+and+Joakim+Nivre%2E+2013%2E+Target+Language+Adaptation+of+Discriminative+Transfer+Parsers%2E+In+NAACL%2C+pages+1061%E2%80%931071%2E)
29. Daniel Zeman and Philip Resnik. 2008. Cross-Language Parser Adaptation between Related Languages. In IJCNLP, pages 35–42. [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%2C+pages+35%E2%80%9342%2E)
30. Yuan Zhang and Regina Barzilay. 2015. Hierarchical Low-Rank Tensors for Multilingual Transfer Parsing. In EMNLP, pages 1857–1867. [find](https://scholar.google.com/scholar?q=Yuan+Zhang+and+Regina+Barzilay%2E+2015%2E+Hierarchical+Low%2DRank+Tensors+for+Multilingual+Transfer+Parsing%2E+In+EMNLP%2C+pages+1857%E2%80%931867%2E)
31. Thomas Müller, Helmut Schmid, and Hinrich Schütze. 2013. Efficient Higher-Order CRFs for Morphological Tagging. In EMNLP, pages 322–332. [find](https://scholar.google.com/scholar?q=Thomas+Mu%CC%88ller%2C+Helmut+Schmid%2C+and+Hinrich+Schu%CC%88tze%2E+2013%2E+Efficient+Higher%2DOrder+CRFs+for+Morphological+Tagging%2E+In+EMNLP%2C+pages+322%E2%80%93332%2E)