---
title: "Do We Really Need Fully Unsupervised Cross-Lingual"
description: "The authors test this claim with a large bilingual lexicon induction (BLI) benchmark covering 15… 61 references, cited by 58 papers here."
authors: ["Ivan Vulić", "Goran Glavaš", "Roi Reichart", "Anna Korhonen"]
year: 2019
venue: "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)"
source: "https://aclanthology.org/D19-1449/"
doi: "10.18653/v1/d19-1449"
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/vulic-2019-do-we-really-need-fully/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/vulic-2019-do-we-really-need-fully/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/4/) / Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?

# Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?

**Authors:** [Ivan Vulić](https://md.research.elamur.ai/free/en/authors/ivan-vulic/), [Goran Glavaš](https://md.research.elamur.ai/free/en/authors/goran-glavas/), [Roi Reichart](https://md.research.elamur.ai/free/en/authors/roi-reichart/) and [Anna Korhonen](https://md.research.elamur.ai/free/en/authors/anna-korhonen/) · **Year:** 2019 · **Venue:** [Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2019](https://md.research.elamur.ai/free/en/venues/emnlp/2019/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/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/D19-1449/) · [PDF](https://aclanthology.org/D19-1449.pdf) · [DOI 10.18653/v1/d19-1449](https://doi.org/10.18653/v1/d19-1449) · [OpenAlex](https://openalex.org/W2970037872)

**Citations:** 99 citations (OpenAlex, 2026-10-14) · [58](https://md.research.elamur.ai/free/en/papers/vulic-2019-do-we-really-need-fully/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Fully unsupervised cross-lingual word embeddings (CLWEs) are often promoted as the best option for low-resource and distant language pairs, where translation dictionaries are scarce. The authors test this claim with a large bilingual lexicon induction (BLI) benchmark covering 15 typologically diverse languages, which gives 210 language pairs. They split projection-based methods into three parts: unsupervised seed extraction (C1), iterative self-learning (C2), and pre-/post-processing (C3). They then apply C2 and C3 from VECMAP, the strongest unsupervised model, to weakly supervised setups that start from only 500–1,000 translation pairs. The unsupervised version breaks down on many pairs. The weakly supervised variants never fail and always score higher, often by a wide margin. The unsupervised method also collapses when the monolingual vectors come from different domains, and it loses even for closely related languages. The authors conclude that the practical case for fully unsupervised CLWEs is weak. In their view, collecting a small seed lexicon is the more sensible route for under-resourced languages.

## Key points
- Fully unsupervised VECMAP (Artetxe et al., 2018b) produces zero or near-zero BLI scores for 87 of the 210 language pairs.
- Self-learning plus pre-/post-processing, started from a 500 or 1K seed dictionary, beats the unsupervised model in every setup. The best overall configuration is FULL+SL+SYM, which keeps only mutual nearest neighbours.
- In the domain-mismatch probe, 300-dim fastText vectors were trained on 1.1M sentences from EuroParl, Wikipedia or EMEA and evaluated on MUSE test sets. The unsupervised model succeeded only with matching domains and only for English–Spanish. Weakly supervised variants, seeded with 500 pairs or identical strings, worked in every setup.
- Weak supervision also wins for similar language pairs such as Swedish–Danish and Spanish–Catalan.
- All 210 training and test dictionaries are public at github.com/ivulic/panlex-bli.

*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 Cambridge](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) — University, Cambridge, United Kingdom · 155 works · 115,562 citations
- [Technion – Israel Institute of Technology](https://md.research.elamur.ai/free/en/universities/technion-israel-institute-of-technology/) — University, Haifa, Israel · 28 works · 4,941 citations
- [University of Mannheim](https://md.research.elamur.ai/free/en/universities/university-of-mannheim/) — University, Mannheim, Germany · 18 works · 6,984 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 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 (1): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 467 works

## Cite

Cite as: Ivan Vulić, Goran Glavaš, Roi Reichart and Anna Korhonen. 2019. Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).

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

```bibtex
@inproceedings{vulic2019do,
  title = {{Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?}},
  author = {Ivan Vulić, Goran Glavaš, Roi Reichart and Anna Korhonen},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},
  year = {2019},
  doi = {10.18653/v1/d19-1449},
  url = {https://doi.org/10.18653/v1/d19-1449}
}
```

- [← previous Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces](https://md.research.elamur.ai/free/en/papers/patra-2019-bilingual-lexicon-induction-semi-supervision/)
- [next → Scoring Sentence Singletons and Pairs for Abstractive Summarization](https://md.research.elamur.ai/free/en/papers/lebanoff-2019-scoring-sentence-singletons-pairs-abstractive/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/4/)

## References

61 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Oliver Adams, Adam Makarucha, Graham Neubig, Steven Bird, and Trevor Cohn. 2017. Cross-lingual word embeddings for low-resource language modeling. In Proceedings of EACL, pages 937–947. [find](https://scholar.google.com/scholar?q=Oliver+Adams%2C+Adam+Makarucha%2C+Graham+Neubig%2C+Steven+Bird%2C+and+Trevor+Cohn%2E+2017%2E+Cross%2Dlingual+word+embeddings+for+low%2Dresource+language+modeling%2E+In+Proceedings+of+EACL%2C+pages+937%E2%80%93947%2E)
2. Rami Al-Rfou, Bryan Perozzi, and Steven Skiena. 2013. [Polyglot: Distributed word representations for multilingual NLP](https://md.research.elamur.ai/free/en/papers/rfou-2013-polyglot-distributed-word-representations-multilingual/). In Proceedings of CoNLL, pages 183–192.
3. Jean Alaux, Edouard Grave, Marco Cuturi, and Armand Joulin. 2019. Unsupervised hyperalignment for multilingual word embeddings. In Proceedings of ICLR. [find](https://scholar.google.com/scholar?q=Jean+Alaux%2C+Edouard+Grave%2C+Marco+Cuturi%2C+and+Armand+Joulin%2E+2019%2E+Unsupervised+hyperalignment+for+multilingual+word+embeddings%2E+In+Proceedings+of+ICLR%2E)
4. David Alvarez-Melis and Tommi Jaakkola. 2018. [Gromov-Wasserstein alignment of word embedding spaces](https://md.research.elamur.ai/free/en/papers/melis-2018-gromov-wasserstein-alignment-word-embedding/). In Proceedings of EMNLP, pages 1881– 1890. [https://asjp.clld.org/](https://asjp.clld.org/) [↗](https://asjp.clld.org/)
5. Mikel Artetxe, Gorka Labaka, and Eneko Agirre. 2017. [Learning bilingual word embeddings with (almost) no bilingual data](https://md.research.elamur.ai/free/en/papers/artetxe-2017-learning-bilingual-word-embeddings-almost/). In Proceedings of ACL, pages 451–462.
6. Zi-Yi Dou, Zhi-Hao Zhou, and Shujian Huang. 2018. Unsupervised bilingual lexicon induction via latent variable models. In Proceedings of EMNLP, pages 621–626. [find](https://scholar.google.com/scholar?q=Zi%2DYi+Dou%2C+Zhi%2DHao+Zhou%2C+and+Shujian+Huang%2E+2018%2E+Unsupervised+bilingual+lexicon+induction+via+latent+variable+models%2E+In+Proceedings+of+EMNLP%2C+pages+621%E2%80%93626%2E)
7. Mikel Artetxe, Gorka Labaka, and Eneko Agirre. 2018a. Generalizing and improving bilingual word embedding mappings with a multi-step framework of linear transformations. In Proceedings of AAAI, pages 5012–5019. [find](https://scholar.google.com/scholar?q=Mikel+Artetxe%2C+Gorka+Labaka%2C+and+Eneko+Agirre%2E+2018a%2E+Generalizing+and+improving+bilingual+word+embedding+mappings+with+a+multi%2Dstep+framework+of+linear+transformations%2E+In+Proceedings+of+AAAI%2C+pages+)
8. Yerai Doval, Jose Camacho-Collados, Luis Espinosa-Anke, and Steven Schockaert. 2019. On the robustness of unsupervised and semi-supervised cross-lingual word embedding learning. CoRR, abs/1908.07742. [find](https://scholar.google.com/scholar?q=Yerai+Doval%2C+Jose+Camacho%2DCollados%2C+Luis+Espinosa%2DAnke%2C+and+Steven+Schockaert%2E+2019%2E+On+the+robustness+of+unsupervised+and+semi%2Dsupervised+cross%2Dlingual+word+embedding+learning%2E+CoRR%2C+abs%2F1908%2E07742%2E)
9. Mikel Artetxe, Gorka Labaka, and Eneko Agirre. 2018b. [A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings](https://md.research.elamur.ai/free/en/papers/artetxe-2018-vecmap-unsupervised/). In Proceedings of ACL, pages 789–798.
10. Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Kyunghyun Cho. 2018c. [Unsupervised neural machine translation](https://md.research.elamur.ai/free/en/papers/artetxe-2017-unsupervised-neural-machine-translation/). In Proceedings of ICLR.
11. Long Duong, Hiroshi Kanayama, Tengfei Ma, Steven Bird, and Trevor Cohn. 2016. Learning crosslingual word embeddings without bilingual corpora. In Proceedings of EMNLP, pages 1285–1295. [find](https://scholar.google.com/scholar?q=Long+Duong%2C+Hiroshi+Kanayama%2C+Tengfei+Ma%2C+Steven+Bird%2C+and+Trevor+Cohn%2E+2016%2E+Learning+crosslingual+word+embeddings+without+bilingual+corpora%2E+In+Proceedings+of+EMNLP%2C+pages+1285%E2%80%931295%2E)
12. Manaal Faruqui and Chris Dyer. 2014. [Improving vector space word representations using multilingual correlation](https://md.research.elamur.ai/free/en/papers/faruqui-2014-improving-vector-space-word-representations/). In Proceedings of EACL, pages 462– 471.
13. Timothy Baldwin, Jonathan Pool, and Susan Colowick. 2010. PanLex and LEXTRACT: Translating all words of all languages of the world. In Proceedings of COLING (Demo Papers), pages 37–40. [find](https://scholar.google.com/scholar?q=Timothy+Baldwin%2C+Jonathan+Pool%2C+and+Susan+Colowick%2E+2010%2E+PanLex+and+LEXTRACT%3A+Translating+all+words+of+all+languages+of+the+world%2E+In+Proceedings+of+COLING+%28Demo+Papers%29%2C+pages+37%E2%80%9340%2E)
14. Daniela Gerz, Ivan Vulić, Edoardo Maria Ponti, Roi Reichart, and Anna Korhonen. 2018. [On the relation between linguistic typology and (limitations of) multilingual language modeling](https://md.research.elamur.ai/free/en/papers/gerz-2018-relation-between-linguistic-typology-limitations/). In Proceedings of EMNLP, pages 316–327.
15. Antonio Valerio Miceli Barone. 2016. Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders. In Proceedings of the 1st Workshop on Representation Learning for NLP, pages 121–126. [find](https://scholar.google.com/scholar?q=Antonio+Valerio+Miceli+Barone%2E+2016%2E+Towards+cross%2Dlingual+distributed+representations+without+parallel+text+trained+with+adversarial+autoencoders%2E+In+Proceedings+of+the+1st+Workshop+on+Representation)
16. Goran Glavaš, Marc Franco-Salvador, Simone P Ponzetto, and Paolo Rosso. 2018. A resource-light method for cross-lingual semantic textual similarity. Knowledge-Based Systems, 143:1–9. [find](https://scholar.google.com/scholar?q=Goran+Glava%C5%A1%2C+Marc+Franco%2DSalvador%2C+Simone+P+Ponzetto%2C+and+Paolo+Rosso%2E+2018%2E+A+resource%2Dlight+method+for+cross%2Dlingual+semantic+textual+similarity%2E+Knowledge%2DBased+Systems%2C+143%3A1%E2%80%939%2E)
17. Anthony Bell and Terrence Sejnowski. 1997. The ’Independent Components’ of Natural Scenes are Edge Filters. Vision Research. [find](https://scholar.google.com/scholar?q=Anthony+Bell+and+Terrence+Sejnowski%2E+1997%2E+The+%E2%80%99Independent+Components%E2%80%99+of+Natural+Scenes+are+Edge+Filters%2E+Vision+Research%2E)
18. Goran Glavaš, Robert Litschko, Sebastian Ruder, and Ivan Vulić. 2019. How to (properly) evaluate cross-lingual word embeddings: On strong baselines, comparative analyses, and some misconceptions. In Proceedings of ACL, pages 710–721. [find](https://scholar.google.com/scholar?q=Goran+Glava%C5%A1%2C+Robert+Litschko%2C+Sebastian+Ruder%2C+and+Ivan+Vulic%CC%81%2E+2019%2E+How+to+%28properly%29+evaluate+cross%2Dlingual+word+embeddings%3A+On+strong+baselines%2C+comparative+analyses%2C+and+some+misconceptions%2E+In+)
19. Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. [Enriching word vectors with subword information](https://md.research.elamur.ai/free/en/papers/bojanowski-2017-enriching-word-vectors-subword-information/). Transactions of the ACL, 5:135–146.
20. Stephan Gouws, Yoshua Bengio, and Greg Corrado. 2015. BilBOWA: Fast bilingual distributed representations without word alignments. In Proceedings of ICML, pages 748–756. [find](https://scholar.google.com/scholar?q=Stephan+Gouws%2C+Yoshua+Bengio%2C+and+Greg+Corrado%2E+2015%2E+BilBOWA%3A+Fast+bilingual+distributed+representations+without+word+alignments%2E+In+Proceedings+of+ICML%2C+pages+748%E2%80%93756%2E)
21. Danqi Chen and Christopher Manning. 2014. [A fast and accurate dependency parser using neural networks](https://md.research.elamur.ai/free/en/papers/chen-2014-fast-accurate-dependency-parser-neural/). In Proceedings of EMNLP, pages 740–750.
22. Stephan Gouws and Anders Søgaard. 2015. Simple task-specific bilingual word embeddings. In Proceedings of NAACL-HLT, pages 1386–1390. [find](https://scholar.google.com/scholar?q=Stephan+Gouws+and+Anders+S%C3%B8gaard%2E+2015%2E+Simple+task%2Dspecific+bilingual+word+embeddings%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+1386%E2%80%931390%2E)
23. Xilun Chen and Claire Cardie. 2018. Unsupervised multilingual word embeddings. In Proceedings of EMNLP, pages 261–270. [find](https://scholar.google.com/scholar?q=Xilun+Chen+and+Claire+Cardie%2E+2018%2E+Unsupervised+multilingual+word+embeddings%2E+In+Proceedings+of+EMNLP%2C+pages+261%E2%80%93270%2E)
24. Edouard Grave, Piotr Bojanowski, Prakhar Gupta, Armand Joulin, and Tomas Mikolov. 2018. [Learning word vectors for 157 languages](https://md.research.elamur.ai/free/en/papers/grave-2018-learning-word-vectors-157-languages/). In Proceedings of LREC, pages 3483–3487.
25. Alexis Conneau, Guillaume Lample, Marc’Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou. 2018a. Word translation without parallel data. In Proceedings of ICLR. [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Guillaume+Lample%2C+Marc%E2%80%99Aurelio+Ranzato%2C+Ludovic+Denoyer%2C+and+Herv%C3%A9+J%C3%A9gou%2E+2018a%2E+Word+translation+without+parallel+data%2E+In+Proceedings+of+ICLR%2E)
26. Jiang Guo, Wanxiang Che, David Yarowsky, Haifeng Wang, and Ting Liu. 2015. [Cross-lingual dependency parsing based on distributed representations](https://md.research.elamur.ai/free/en/papers/guo-2015-cross-lingual-dependency-parsing-based/). In Proceedings of ACL, pages 1234–1244.
27. Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel Bowman, Holger Schwenk, and Veselin Stoyanov. 2018b. XNLI: Evaluating cross-lingual sentence representations. In Proceedings of EMNLP, pages 2475–2485. [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Ruty+Rinott%2C+Guillaume+Lample%2C+Adina+Williams%2C+Samuel+Bowman%2C+Holger+Schwenk%2C+and+Veselin+Stoyanov%2E+2018b%2E+XNLI%3A+Evaluating+cross%2Dlingual+sentence+representations%2E+In+Proceedings+of+EM)
28. Geert Heyman, Bregt Verreet, Ivan Vulić, and Marie-Francine Moens. 2019. Learning unsupervised multilingual word embeddings with incremental multilingual hubs. In Proceedings of NAACL-HLT, pages 1890–1902. [find](https://scholar.google.com/scholar?q=Geert+Heyman%2C+Bregt+Verreet%2C+Ivan+Vulic%CC%81%2C+and+Marie%2DFrancine+Moens%2E+2019%2E+Learning+unsupervised+multilingual+word+embeddings+with+incremental+multilingual+hubs%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+1890)
29. Ryan Cotterell, Sebastian J. Mielke, Jason Eisner, and Brian Roark. 2018. [Are all languages equally hard to language-model?](https://md.research.elamur.ai/free/en/papers/cotterell-2018-are-all-languages-equally-hard/) In Proceedings of NAACL-HLT.
30. Geert Heyman, Ivan Vulić, and Marie-Francine Moens. 2017. Bilingual lexicon induction by learning to combine word-level and character-level representations. In Proceedings of EACL, pages 1085–1095. [find](https://scholar.google.com/scholar?q=Geert+Heyman%2C+Ivan+Vulic%CC%81%2C+and+Marie%2DFrancine+Moens%2E+2017%2E+Bilingual+lexicon+induction+by+learning+to+combine+word%2Dlevel+and+character%2Dlevel+representations%2E+In+Proceedings+of+EACL%2C+pages+1085%E2%80%931095%2E)
31. Yedid Hoshen and Lior Wolf. 2018. Non-adversarial unsupervised word translation. In Proceedings of EMNLP, pages 469–478. [find](https://scholar.google.com/scholar?q=Yedid+Hoshen+and+Lior+Wolf%2E+2018%2E+Non%2Dadversarial+unsupervised+word+translation%2E+In+Proceedings+of+EMNLP%2C+pages+469%E2%80%93478%2E)
32. Tasnim Mohiuddin and Shafiq Joty. 2019. Revisiting adversarial autoencoder for unsupervised word translation with cycle consistency and improved training. In Proceedings of NAACL-HLT, pages 3857–3867. [find](https://scholar.google.com/scholar?q=Tasnim+Mohiuddin+and+Shafiq+Joty%2E+2019%2E+Revisiting+adversarial+autoencoder+for+unsupervised+word+translation+with+cycle+consistency+and+improved+training%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+3857%E2%80%933867%2E)
33. David Kamholz, Jonathan Pool, and Susan M. Colowick. 2014. Panlex: Building a resource for panlingual lexical translation. In Proceedings of LREC, pages 3145–3150. [find](https://scholar.google.com/scholar?q=David+Kamholz%2C+Jonathan+Pool%2C+and+Susan+M%2E+Colowick%2E+2014%2E+Panlex%3A+Building+a+resource+for+panlingual+lexical+translation%2E+In+Proceedings+of+LREC%2C+pages+3145%E2%80%933150%2E)
34. Ndapa Nakashole. 2018. NORMA: Neighborhood sensitive maps for multilingual word embeddings. In Proceedings of EMNLP, pages 512–522. [find](https://scholar.google.com/scholar?q=Ndapa+Nakashole%2E+2018%2E+NORMA%3A+Neighborhood+sensitive+maps+for+multilingual+word+embeddings%2E+In+Proceedings+of+EMNLP%2C+pages+512%E2%80%93522%2E)
35. Yova Kementchedjhieva, Sebastian Ruder, Ryan Cotterell, and Anders Søgaard. 2018. Generalizing Procrustes analysis for better bilingual dictionary induction. In Proceedings of CoNLL, pages 211–220. [find](https://scholar.google.com/scholar?q=Yova+Kementchedjhieva%2C+Sebastian+Ruder%2C+Ryan+Cotterell%2C+and+Anders+S%C3%B8gaard%2E+2018%2E+Generalizing+Procrustes+analysis+for+better+bilingual+dictionary+induction%2E+In+Proceedings+of+CoNLL%2C+pages+211%E2%80%93220%2E)
36. Aitor Ormazabal, Mikel Artetxe, Gorka Labaka, Aitor Soroa, and Eneko Agirre. 2019. Analyzing the limitations of cross-lingual word embedding mappings. In Proceedings of ACL, pages 4990–4995. [find](https://scholar.google.com/scholar?q=Aitor+Ormazabal%2C+Mikel+Artetxe%2C+Gorka+Labaka%2C+Aitor+Soroa%2C+and+Eneko+Agirre%2E+2019%2E+Analyzing+the+limitations+of+cross%2Dlingual+word+embedding+mappings%2E+In+Proceedings+of+ACL%2C+pages+4990%E2%80%934995%2E)
37. Yunsu Kim, Jiahui Geng, and Hermann Ney. 2018. Improving unsupervised word-by-word translation with language model and denoising autoencoder. In Proceedings of EMNLP, pages 862–868. [find](https://scholar.google.com/scholar?q=Yunsu+Kim%2C+Jiahui+Geng%2C+and+Hermann+Ney%2E+2018%2E+Improving+unsupervised+word%2Dby%2Dword+translation+with+language+model+and+denoising+autoencoder%2E+In+Proceedings+of+EMNLP%2C+pages+862%E2%80%93868%2E)
38. Sebastian Ruder, Ivan Vulić, and Anders Søgaard. 2019. A survey of cross-lingual word embedding models. Journal of Artificial Intelligence Research, 65:569–631. [find](https://scholar.google.com/scholar?q=Sebastian+Ruder%2C+Ivan+Vulic%CC%81%2C+and+Anders+S%C3%B8gaard%2E+2019%2E+A+survey+of+cross%2Dlingual+word+embedding+models%2E+Journal+of+Artificial+Intelligence+Research%2C+65%3A569%E2%80%93631%2E)
39. Alexandre Klementiev, Ivan Titov, and Binod Bhattarai. 2012. [Inducing crosslingual distributed representations of words](https://md.research.elamur.ai/free/en/papers/klementiev-2012-inducing-crosslingual-distributed-representations-words/). Proceedings of COLING, pages 1459–1474.
40. Samuel L. Smith, David H.P. Turban, Steven Hamblin, and Nils Y. Hammerla. 2017. [Offline bilingual word vectors, orthogonal transformations and the inverted softmax](https://md.research.elamur.ai/free/en/papers/smith-2017-offline-bilingual-word-vectors-orthogonal/). In Proceedings of ICLR.
41. Philipp Koehn. 2005. Europarl: A parallel corpus for statistical machine translation. In Proceedings of the 10th Machine Translation Summit (MT SUMMIT), pages 79–86. [find](https://scholar.google.com/scholar?q=Philipp+Koehn%2E+2005%2E+Europarl%3A+A+parallel+corpus+for+statistical+machine+translation%2E+In+Proceedings+of+the+10th+Machine+Translation+Summit+%28MT+SUMMIT%29%2C+pages+79%E2%80%9386%2E)
42. Guillaume Lample, Alexis Conneau, Ludovic Denoyer, and Marc’Aurelio Ranzato. 2018a. [Unsupervised machine translation using monolingual corpora only](https://md.research.elamur.ai/free/en/papers/lample-2017-unsupervised-machine-translation-using-monolingual/). In Proceedings of ICLR.
43. Anders Søgaard, Željko Agić, Héctor Martínez Alonso, Barbara Plank, Bernd Bohnet, and Anders Johannsen. 2015. Inverted indexing for cross-lingual NLP. In Proceedings of ACL, pages 1713–1722. [find](https://scholar.google.com/scholar?q=Anders+S%C3%B8gaard%2C+%C5%BDeljko+Agic%CC%81%2C+H%C3%A9ctor+Mart%C3%ADnez+Alonso%2C+Barbara+Plank%2C+Bernd+Bohnet%2C+and+Anders+Johannsen%2E+2015%2E+Inverted+indexing+for+cross%2Dlingual+NLP%2E+In+Proceedings+of+ACL%2C+pages+1713%E2%80%931722%2E)
44. Anders Søgaard, Sebastian Ruder, and Ivan Vulić. 2018. [On the limitations of unsupervised bilingual dictionary induction](https://md.research.elamur.ai/free/en/papers/sogaard-2018-limitations-unsupervised-bilingual-dictionary-induction/). In Proceedings of ACL, pages 778–788.
45. Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, and Marc’Aurelio Ranzato. 2018b. Phrase-based & neural unsupervised machine translation. In Proceedings of EMNLP, pages 5039– 5049. [find](https://scholar.google.com/scholar?q=Guillaume+Lample%2C+Myle+Ott%2C+Alexis+Conneau%2C+Ludovic+Denoyer%2C+and+Marc%E2%80%99Aurelio+Ranzato%2E+2018b%2E+Phrase%2Dbased+%26+neural+unsupervised+machine+translation%2E+In+Proceedings+of+EMNLP%2C+pages+5039%E2%80%93+5049%2E)
46. Jörg Tiedemann. 2009. News from OPUS - A collection of multilingual parallel corpora with tools and interfaces. In Proceedings of RANLP, pages 237– 248. [find](https://scholar.google.com/scholar?q=J%C3%B6rg+Tiedemann%2E+2009%2E+News+from+OPUS+%2D+A+collection+of+multilingual+parallel+corpora+with+tools+and+interfaces%2E+In+Proceedings+of+RANLP%2C+pages+237%E2%80%93+248%2E)
47. Robert Litschko, Goran Glavaš, Ivan Vulic, and Laura Dietz. 2019. Evaluating resource-lean cross-lingual embedding models in unsupervised retrieval. In Proceedings of SIGIR, pages 1109–1112. [find](https://scholar.google.com/scholar?q=Robert+Litschko%2C+Goran+Glava%C5%A1%2C+Ivan+Vulic%2C+and+Laura+Dietz%2E+2019%2E+Evaluating+resource%2Dlean+cross%2Dlingual+embedding+models+in+unsupervised+retrieval%2E+In+Proceedings+of+SIGIR%2C+pages+1109%E2%80%931112%2E)
48. Joseph Turian, Lev-Arie Ratinov, and Yoshua Bengio. 2010. [Word representations: A simple and general method for semi-supervised learning](https://md.research.elamur.ai/free/en/papers/turian-2010-word-representations-simple-general-method/). In Proceedings of ACL, pages 384–394.
49. Robert Litschko, Goran Glavaš, Simone Paolo Ponzetto, and Ivan Vulić. 2018. Unsupervised cross-lingual information retrieval using monolingual data only. In Proceedings of SIGIR, pages 1253–1256. [find](https://scholar.google.com/scholar?q=Robert+Litschko%2C+Goran+Glava%C5%A1%2C+Simone+Paolo+Ponzetto%2C+and+Ivan+Vulic%CC%81%2E+2018%2E+Unsupervised+cross%2Dlingual+information+retrieval+using+monolingual+data+only%2E+In+Proceedings+of+SIGIR%2C+pages+1253%E2%80%931256%2E)
50. Ivan Vulić and Anna Korhonen. 2016. On the role of seed lexicons in learning bilingual word embeddings. In Proceedings of ACL, pages 247–257. [find](https://scholar.google.com/scholar?q=Ivan+Vulic%CC%81+and+Anna+Korhonen%2E+2016%2E+On+the+role+of+seed+lexicons+in+learning+bilingual+word+embeddings%2E+In+Proceedings+of+ACL%2C+pages+247%E2%80%93257%2E)
51. Noa Yehezkel Lubin, Jacob Goldberger, and Yoav Goldberg. 2019. Aligning vector-spaces with noisy supervised lexicon. In Proceedings of NAACL-HLT, pages 460–465. [find](https://scholar.google.com/scholar?q=Noa+Yehezkel+Lubin%2C+Jacob+Goldberger%2C+and+Yoav+Goldberg%2E+2019%2E+Aligning+vector%2Dspaces+with+noisy+supervised+lexicon%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+460%E2%80%93465%2E)
52. Ivan Vulić and Marie-Francine Moens. 2015. Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings. In Proceedings of SIGIR, pages 363–372. [find](https://scholar.google.com/scholar?q=Ivan+Vulic%CC%81+and+Marie%2DFrancine+Moens%2E+2015%2E+Monolingual+and+cross%2Dlingual+information+retrieval+models+based+on+%28bilingual%29+word+embeddings%2E+In+Proceedings+of+SIGIR%2C+pages+363%E2%80%93372%2E)
53. Tomas Mikolov, Quoc V Le, and Ilya Sutskever. 2013a. Exploiting similarities among languages for machine translation. CoRR, abs/1309.4168. [find](https://scholar.google.com/scholar?q=Tomas+Mikolov%2C+Quoc+V+Le%2C+and+Ilya+Sutskever%2E+2013a%2E+Exploiting+similarities+among+languages+for+machine+translation%2E+CoRR%2C+abs%2F1309%2E4168%2E)
54. Ivan Vulić, Nikola Mrkšić, and Anna Korhonen. 2017. Cross-lingual induction and transfer of verb classes based on word vector space specialisation. In Proceedings of EMNLP, pages 2536–2548. [find](https://scholar.google.com/scholar?q=Ivan+Vulic%CC%81%2C+Nikola+Mrk%C5%A1ic%CC%81%2C+and+Anna+Korhonen%2E+2017%2E+Cross%2Dlingual+induction+and+transfer+of+verb+classes+based+on+word+vector+space+specialisation%2E+In+Proceedings+of+EMNLP%2C+pages+2536%E2%80%932548%2E)
55. Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S Corrado, and Jeffrey Dean. 2013b. [Distributed Representations of Words and Phrases and their Compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Proceedings of NIPS, pages 3111– 3119.
56. Søren Wichmann, André Müller, Viveka Velupillai, Cecil H Brown, Eric W Holman, Pamela Brown, Sebastian Sauppe, Oleg Belyaev, Matthias Urban, Zarina Molochieva, et al. 2018. The ASJP database (version 18). [find](https://scholar.google.com/scholar?q=S%C3%B8ren+Wichmann%2C+Andr%C3%A9+M%C3%BCller%2C+Viveka+Velupillai%2C+Cecil+H+Brown%2C+Eric+W+Holman%2C+Pamela+Brown%2C+Sebastian+Sauppe%2C+Oleg+Belyaev%2C+Matthias+Urban%2C+Zarina+Molochieva%2C+et+al%2E+2018%2E+The+ASJP+database+%28version+)
57. Chao Xing, Dong Wang, Chao Liu, and Yiye Lin. 2015. [Normalized word embedding and orthogonal transform for bilingual word translation](https://md.research.elamur.ai/free/en/papers/xing-2015-normalized-word-embedding-orthogonal-transform/). In Proceedings of NAACL-HLT, pages 1006–1011.
58. Mozhi Zhang, Keyulu Xu, Ken-ichi Kawarabayashi, Stefanie Jegelka, and Jordan Boyd-Graber. 2019. Are girls neko or shōjo? Cross-lingual alignment of non-isomorphic embeddings with iterative normalization. In Proceedings of ACL, pages 3180–3189. [find](https://scholar.google.com/scholar?q=Mozhi+Zhang%2C+Keyulu+Xu%2C+Ken%2Dichi+Kawarabayashi%2C+Stefanie+Jegelka%2C+and+Jordan+Boyd%2DGraber%2E+2019%2E+Are+girls+neko+or+sho%CC%84jo%3F+Cross%2Dlingual+alignment+of+non%2Disomorphic+embeddings+with+iterative+normalizat)
59. Yuan Zhang, David Gaddy, Regina Barzilay, and Tommi Jaakkola. 2016. Ten pairs to tag – Multilingual POS tagging via coarse mapping between embeddings. In Proceedings of NAACL-HLT, pages 1307–1317. [find](https://scholar.google.com/scholar?q=Yuan+Zhang%2C+David+Gaddy%2C+Regina+Barzilay%2C+and+Tommi+Jaakkola%2E+2016%2E+Ten+pairs+to+tag+%E2%80%93+Multilingual+POS+tagging+via+coarse+mapping+between+embeddings%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+1307%E2%80%931317%2E)
60. George Kingsley Zipf. 1949. Human behavior and the principle of least effort: An introduction to human ecology. [find](https://scholar.google.com/scholar?q=George+Kingsley+Zipf%2E+1949%2E+Human+behavior+and+the+principle+of+least+effort%3A+An+introduction+to+human+ecology%2E)
61. Yftah Ziser and Roi Reichart. 2018. Deep pivot-based modeling for cross-language cross-domain transfer with minimal guidance. In Proceedings of EMNLP, pages 238–249. [find](https://scholar.google.com/scholar?q=Yftah+Ziser+and+Roi+Reichart%2E+2018%2E+Deep+pivot%2Dbased+modeling+for+cross%2Dlanguage+cross%2Ddomain+transfer+with+minimal+guidance%2E+In+Proceedings+of+EMNLP%2C+pages+238%E2%80%93249%2E)

*Updated 24 October 2026*