---
title: "Adversarial Training for Unsupervised Bilingual — Zhang 2017"
description: "Bilingual lexicon induction usually depends on cross-lingual supervision to connect independently trained word embedding spaces, such as a parallel…"
authors: ["Meng Zhang", "Yang Liu", "Huanbo Luan", "Maosong Sun"]
year: 2017
venue: "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P17-1179/"
doi: "10.18653/v1/p17-1179"
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/zhang-2017-adversarial-training-unsupervised-bilingual-lexicon/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2017-adversarial-training-unsupervised-bilingual-lexicon/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/) / Adversarial Training for Unsupervised Bilingual Lexicon Induction

# Adversarial Training for Unsupervised Bilingual Lexicon Induction

**Authors:** [Meng Zhang](https://md.research.elamur.ai/free/en/authors/meng-zhang/), [Yang Liu](https://md.research.elamur.ai/free/en/authors/yang-liu/), [Huanbo Luan](https://md.research.elamur.ai/free/en/authors/huanbo-luan/), [Maosong Sun](https://md.research.elamur.ai/free/en/authors/maosong-sun/) · **Institutions:** [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) · [State Key Laboratory of Intelligent Technology and Systems](https://md.research.elamur.ai/free/en/labs/state-key-laboratory-of-intelligent-technology-and-systems/) · **Year:** 2017 · **Venue:** Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/P17-1179/) · [PDF](https://aclanthology.org/P17-1179.pdf) · [DOI 10.18653/v1/p17-1179](https://doi.org/10.18653/v1/p17-1179) · [OpenAlex](https://openalex.org/W2740132093)

**Citations:** 256 citations (OpenAlex, 2026-10-14) · [103](https://md.research.elamur.ai/free/en/papers/zhang-2017-adversarial-training-unsupervised-bilingual-lexicon/cited-by/) in our library, of the 140884 papers whose bibliographies we read

## Summary
Bilingual lexicon induction usually depends on cross-lingual supervision to connect independently trained word embedding spaces, such as a parallel corpus or a seed dictionary of hundreds to thousands of word pairs. This paper shows that the connection can be learned with no cross-lingual signal at all. The authors treat the task as a generative adversarial game. A generator, which is a linear map, transforms source-language embeddings. A discriminator tries to tell these mapped vectors apart from genuine target-language embeddings. Because the game aligns whole distributions, it never needs word translation pairs.

They propose three variants: a unidirectional map, a bidirectional map with tied (transposed) weights, and an adversarial autoencoder with a reconstruction term. Training is unstable, so they also report practical techniques for it, including noise-based regularization of the discriminator and an unsupervised way to choose checkpoints.

On a replicated French-English setup that uses no cross-lingual signal, the method clearly beats MonoGiza and the approach of Cao et al. (2016). This matters for low-resource languages and domains that have plain text but lack parallel data.

## Key points
- **Inputs:** CBOW embeddings trained with word2vec using default settings, dimension 50 by default, normalized to unit length. Frequent words are down-weighted when sampling for training.
- **Model design:**
  - The generator is a d×d matrix. Non-linear generators failed, which the authors link to a risk similar to mode collapse.
  - The discriminator is a feed-forward network with one hidden layer, trained with cross-entropy on mini-batches of 128.
- **Three architectures:**
  - Model 1 is unidirectional.
  - Model 2 is bidirectional, with G and Gᵀ and two discriminators.
  - Model 3 is an adversarial autoencoder with a cosine reconstruction loss weighted by λ. Setting λ = 0 reduces it to Model 1.
- **Discriminator regularization:** the best option was multiplicative Gaussian noise (σ = 0.5) on both the input and hidden layer. Additive Gaussian noise worked about as well, and dropout and l2 regularization also helped.
- **Comparison with Cao et al. (2016):** in the replicated French-English experiment, evaluated with top-5 accuracy against a noisy lexicon derived from word alignment, the approach outperformed both MonoGiza and Cao et al. (2016). Earlier adversarial work by Barone (2016) had reported negative results.

## Interesting ideas
- **Unsupervised checkpoint selection.** Training does not converge, but sudden drops in generator loss coincide with drops in discriminator accuracy and with good models. Saving the checkpoint with the lowest generator loss avoids the need for a labeled validation set. The same trick could apply to other unsupervised GAN-style alignment tasks.
- **Limiting generator capacity on purpose.** A linear, near-orthogonal map stops the generator from collapsing everything onto a single point. Restricting the hypothesis space can stabilize adversarial matching more effectively than adding capacity.
- **Soft orthogonality.** The authors avoid expensive constrained optimization by encouraging orthogonality softly, through tied transposed weights or a reconstruction loss. They also observed that good solutions become nearly orthogonal on their own, which suggests ‖GᵀG − I‖ is a useful diagnostic to monitor.
- **Using loss curves to judge hyperparameters.** A configuration that shows no clear loss drop and just keeps oscillating is probably bad. This offers a cheap label-free signal for tuning.
- **Treating the evaluation lexicon as part of the setup.** Lexicons built from automatic word alignment can list many translations per word, which inflates scores. It is worth checking how the ground-truth lexicon was built before comparing numbers across papers.

*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: [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/)

## Cite

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

```bibtex
@inproceedings{zhang2017adversarial,
  title = {{Adversarial Training for Unsupervised Bilingual Lexicon Induction}},
  author = {Zhang, Meng and Liu, Yang and Luan, Huanbo and Sun, Maosong},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2017},
  doi = {10.18653/v1/p17-1179},
  url = {https://doi.org/10.18653/v1/p17-1179}
}
```

- [← previous Attention-based Recurrent Convolutional Neural Network for Automatic Essay Scoring](https://md.research.elamur.ai/free/en/papers/dong-2017-attention-based-recurrent-convolutional-neural/)
- [next → Exploring Neural Text Simplification Models](https://md.research.elamur.ai/free/en/papers/nisioi-2017-exploring-neural-text-simplification-models/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/)

## References

61 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Waleed Ammar, George Mulcaire, Yulia Tsvetkov, Guillaume Lample, Chris Dyer, and Noah A. Smith. 2016. Massively Multilingual Word Embeddings. arXiv:1602.01925 [cs] http://arxiv.org/abs/ 1602.01925. [↗](http://arxiv.org/abs/) [our card](https://md.research.elamur.ai/free/en/papers/ammar-2016-massively-multilingual-word-embeddings/)
2. Martin Arjovsky and Léon Bottou. 2017. Towards Principled Methods For Training Generative Adversarial Networks. In ICLR. http://arxiv.org/abs/ 1701.04862. [↗](http://arxiv.org/abs/)
3. Mikel Artetxe, Gorka Labaka, and Eneko Agirre. 2016. Learning principled bilingual mappings of word embeddings while preserving monolingual invariance. In EMNLP. [http://aclanthology.info/](http://aclanthology.info/) papers/learning-principled-bilingual-mappings-of-word-embeddings-while-preserving-monolingual-invariance. [↗](http://aclanthology.info/) [our card](https://md.research.elamur.ai/free/en/papers/artetxe-2016-learning-principled-bilingual-mappings-word/)
4. 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. https://doi.org/10.18653/v1/ W16-1614. [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)
5. Chris M. Bishop. 1995. Training with Noise is Equivalent to Tikhonov Regularization. Neural Comput. https://doi.org/10.1162/neco.1995.7.1.108. — [doi:10.1162/neco.1995.7.1.108](https://doi.org/10.1162/neco.1995.7.1.108) [↗](https://doi.org/10.1162/neco.1995.7.1.108)
6. Hailong Cao, Tiejun Zhao, Shu Zhang, and Yao Meng. 2016. A Distribution-based Model to Learn Bilingual Word Embeddings. In COL-ING. [http://aclanthology.info/papers/a-distribution-based-model-to-learn-bilingual-word-embeddings](http://aclanthology.info/papers/a-distribution-based-model-to-learn-bilingual-word-embeddings). [↗](http://aclanthology.info/papers/a-distribution-based-model-to-learn-bilingual-word-embeddings)
7. Sarath Chandar A P, Stanislas Lauly, Hugo Larochelle, Mitesh Khapra, Balaraman Ravindran, Vikas C Raykar, and Amrita Saha. 2014. An Autoencoder Approach to Learning Bilingual Word Representations. In NIPS. [http://papers.nips.cc/](http://papers.nips.cc/) paper/5270-an-autoencoder-approach-to-learning-bilingual-word-represent… [↗](http://papers.nips.cc/)
8. Xilun Chen, Yu Sun, Ben Athiwaratkun, Claire Cardie, and Kilian Weinberger. 2016. Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification. arXiv:1606.01614 [cs] http://arxiv.org/abs/1606.01614. [↗](http://arxiv.org/abs/1606.01614) [our card](https://md.research.elamur.ai/free/en/papers/chen-2018-adversarial-deep-averaging-networks-cross/)
9. Jocelyn Coulmance, Jean-Marc Marty, Guillaume Wenzek, and Amine Benhalloum. 2015. Trans-gram, Fast Cross-lingual Word-embeddings. In EMNLP. [http://aclanthology.info/papers/trans-gram-fast-cross-lingual-word-embeddings](http://aclanthology.info/papers/trans-gram-fast-cross-lingual-word-embeddings). [↗](http://aclanthology.info/papers/trans-gram-fast-cross-lingual-word-embeddings)
10. Qing Dou and Kevin Knight. 2012. Large scale decipherment for out-of-domain machine translation. In EMNLP-CoNLL. [http://aclweb.org/anthology/D12-1025](http://aclweb.org/anthology/D12-1025). [↗](http://aclweb.org/anthology/D12-1025)
11. Qing Dou and Kevin Knight. 2013. Dependency-Based Decipherment for Resource-Limited Machine Translation. In EMNLP. [http://aclanthology.info/](http://aclanthology.info/) papers/dependency-based-decipherment-for-resource-limited-machine-translation. [↗](http://aclanthology.info/)
12. Qing Dou, Ashish Vaswani, Kevin Knight, and Chris Dyer. 2015. Unifying Bayesian Inference and Vector Space Models for Improved Decipherment. In ACL-IJCNLP. [http://www.aclweb.org/anthology/](http://www.aclweb.org/anthology/) P15-1081. [↗](http://www.aclweb.org/anthology/)
13. Long Duong, Hiroshi Kanayama, Tengfei Ma, Steven Bird, and Trevor Cohn. 2016. Learning Crosslingual Word Embeddings without Bilingual Corpora. In EMNLP. [http://aclanthology.info/](http://aclanthology.info/) papers/learning-crosslingual-word-embeddings-without-bilingual-corpora. [↗](http://aclanthology.info/)
14. Manaal Faruqui and Chris Dyer. 2014. Improving Vector Space Word Representations Using Multilingual Correlation. In EACL. http:/ /aclanthology.info/papers/improving-vector-space-word-representations-using-multilingual-correlation. [find](https://scholar.google.com/scholar?q=Manaal+Faruqui+and+Chris+Dyer%2E+2014%2E+Improving+Vector+Space+Word+Representations+Using+Multilingual+Correlation%2E+In+EACL%2E+http%3A%2F+%2Faclanthology%2Einfo%2Fpapers%2Fimproving%2Dvector%2Dspace%2Dword%2Drepresentations%2Du) [our card](https://md.research.elamur.ai/free/en/papers/faruqui-2014-improving-vector-space-word-representations/)
15. Pascale Fung and Percy Cheung. 2004. Mining Very-Non-Parallel Corpora: Parallel Sentence and Lexicon Extraction via Bootstrapping and EM. In EMNLP. [http://aclweb.org/anthology/W04-3208](http://aclweb.org/anthology/W04-3208). [↗](http://aclweb.org/anthology/W04-3208)
16. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-Adversarial Training of Neural Networks. Journal of Machine Learning Research http:/ /jmlr.org/papers/v17/15-239.html. [find](https://scholar.google.com/scholar?q=Yaroslav+Ganin%2C+Evgeniya+Ustinova%2C+Hana+Ajakan%2C+Pascal+Germain%2C+Hugo+Larochelle%2C+Franc%CC%A7ois+Laviolette%2C+Mario+Marchand%2C+and+Victor+Lempitsky%2E+2016%2E+Domain%2DAdversarial+Training+of+Neural+Networks%2E+Journ)
17. Eric Gaussier, J.M. Renders, I. Matveeva, C. Goutte, and H. Dejean. 2004. A Geometric View on Bilingual Lexicon Extraction from Comparable Corpora. In ACL. https://doi.org/10.3115/1218955.1219022. [↗](https://doi.org/10.3115/1218955.1219022)
18. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In NIPS. [http://papers.nips.cc/](http://papers.nips.cc/) paper/5423-generative-adversarial-nets.pdf. [↗](http://papers.nips.cc/)
19. Hal Daumé III and Jagadeesh Jagarlamudi. 2011. Domain adaptation for machine translation by mining unseen words. In ACL-HLT. [http://aclweb.org/](http://aclweb.org/) anthology/P11-2071. [↗](http://aclweb.org/)
20. Stephan Gouws, Yoshua Bengio, and Greg Corrado. 2015. BilBOWA: Fast Bilingual Distributed Representations without Word Alignments. In ICML. [http://jmlr.org/proceedings/papers/v37/](http://jmlr.org/proceedings/papers/v37/) gouws15.html. [↗](http://jmlr.org/proceedings/papers/v37/)
21. Georgiana Dinu, Angeliki Lazaridou, and Marco Baroni. 2015. Improving Zero-Shot Learning by Mitigating the Hubness Problem. In ICLR Workshop. http://arxiv.org/abs/1412.6568. — [arXiv:1412.6568](https://arxiv.org/abs/1412.6568) [↗](http://arxiv.org/abs/1412.6568)
22. Stephan Gouws and Anders Søgaard. 2015. Simple task-specific bilingual word embeddings. In NAACL-HLT. [http://www.aclweb.org/anthology/](http://www.aclweb.org/anthology/) N15-1157. [↗](http://www.aclweb.org/anthology/)
23. Aria Haghighi, Percy Liang, Taylor Berg-Kirkpatrick, and Dan Klein. 2008. Learning Bilingual Lexicons from Monolingual Corpora. In ACL-HLT. [http://aclanthology.info/papers/learning-bilingual-lexicons-from-monolingual-corpora](http://aclanthology.info/papers/learning-bilingual-lexicons-from-monolingual-corpora). [↗](http://aclanthology.info/papers/learning-bilingual-lexicons-from-monolingual-corpora) [our card](https://md.research.elamur.ai/free/en/papers/haghighi-2008-learning-bilingual-lexicons-monolingual-corpora/)
24. Zakaria Mhammedi, Andrew Hellicar, Ashfaqur Rahman, and James Bailey. 2016. Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections. arXiv:1612.00188 [cs] http://arxiv.org/abs/1612.00188. — [arXiv:1612.00188](https://arxiv.org/abs/1612.00188) [↗](http://arxiv.org/abs/1612.00188)
25. Di He, Yingce Xia, Tao Qin, Liwei Wang, Nenghai Yu, Tieyan Liu, and Wei-Ying Ma. 2016. Dual Learning for Machine Translation. In NIPS. [http://papers.nips.cc/paper/6469-dual-learning-for-machine-translation.pdf](http://papers.nips.cc/paper/6469-dual-learning-for-machine-translation.pdf). [↗](http://papers.nips.cc/paper/6469-dual-learning-for-machine-translation.pdf)
26. Tomas Mikolov, Quoc V Le, and Ilya Sutskever. 2013a. Exploiting Similarities among Languages for Machine Translation. arXiv:1309.4168 [cs] http://arxiv.org/abs/1309.4168. [↗](http://arxiv.org/abs/1309.4168)
27. Karl Moritz Hermann and Phil Blunsom. 2014. Multilingual Distributed Representations without Word Alignment. In ICLR. http://arxiv.org/abs/ 1312.6173. [↗](http://arxiv.org/abs/)
28. Ann Irvine and Chris Callison-Burch. 2013. Combining bilingual and comparable corpora for low resource machine translation. In Proceedings of the Eighth Workshop on Statistical Machine Translation. [http://aclweb.org/anthology/W13-2233](http://aclweb.org/anthology/W13-2233). [↗](http://aclweb.org/anthology/W13-2233)
29. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013b. Distributed Representations of Words and Phrases and their Compositionality. In NIPS. [http://papers.nips.cc/](http://papers.nips.cc/) paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf. [↗](http://papers.nips.cc/) [our card](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/)
30. Shakir Mohamed and Balaji Lakshminarayanan. 2016. Learning in Implicit Generative Models. arXiv:1610.03483 [cs, stat] http://arxiv.org/abs/ 1610.03483. — [arXiv:1610.03483](https://arxiv.org/abs/1610.03483) [↗](http://arxiv.org/abs/)
31. Diederik Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs] http://arxiv.org/abs/ 1412.6980. [↗](http://arxiv.org/abs/)
32. Sebastian Nowozin, Botond Cseke, and Ryota Tomioka. 2016. f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization. arXiv:1606.00709 [cs, stat] [http://arxiv.org/](http://arxiv.org/) abs/1606.00709. — [arXiv:1606.00709](https://arxiv.org/abs/1606.00709) [↗](http://arxiv.org/)
33. Philipp Koehn and Kevin Knight. 2002. Learning a Translation Lexicon from Monolingual Corpora. In ACL Workshop on Unsupervised Lexical Acquisition. https://doi.org/10.3115/1118627.1118629. [↗](https://doi.org/10.3115/1118627.1118629) [our card](https://md.research.elamur.ai/free/en/papers/koehn-2002-learning-translation-lexicon-monolingual-corpora/)
34. Takamasa Oshikiri, Kazuki Fukui, and Hidetoshi Shimodaira. 2016. Cross-Lingual Word Representations via Spectral Graph Embeddings. In ACL. https://doi.org/10.18653/v1/P16-2080. [↗](https://doi.org/10.18653/v1/P16-2080)
35. Tomáš Kočiský, Karl Moritz Hermann, and Phil Blunsom. 2014. Learning Bilingual Word Representations by Marginalizing Alignments. In ACL. [http://aclanthology.info/papers/learning-bilingual-word-representations-by-marginalizing-alignments](http://aclanthology.info/papers/learning-bilingual-word-representations-by-marginalizing-alignments). [↗](http://aclanthology.info/papers/learning-bilingual-word-representations-by-marginalizing-alignments)
36. Angeliki Lazaridou, Georgiana Dinu, and Marco Baroni. 2015. Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning. In ACL-IJCNLP. https://doi.org/10.3115/v1/P15-1027. [↗](https://doi.org/10.3115/v1/P15-1027)
37. Ang Lu, Weiran Wang, Mohit Bansal, Kevin Gimpel, and Karen Livescu. 2015. Deep Multilingual Correlation for Improved Word Embeddings. In NAACL-HLT. [http://aclanthology.info/papers/](http://aclanthology.info/papers/) deep-multilingual-correlation-for-improved-word-embeddings. [↗](http://aclanthology.info/papers/)
38. Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. Bilingual Word Representations with Monolingual Quality in Mind. In Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing. [http://aclanthology.info/papers/bilingual-word-representations-with-monolingual-qual…](http://aclanthology.info/papers/bilingual-word-representations-with-monolingual-qual…) [↗](http://aclanthology.info/papers/bilingual-word-representations-with-monolingual-qual…) [our card](https://md.research.elamur.ai/free/en/papers/luong-2015-bilingual-word-representations-monolingual-quality/)
39. Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow, and Brendan Frey. 2015. Adversarial Autoencoders. arXiv:1511.05644 [cs] http://arxiv.org/abs/1511.05644. — [arXiv:1511.05644](https://arxiv.org/abs/1511.05644) [↗](http://arxiv.org/abs/1511.05644)
40. Alec Radford, Luke Metz, and Soumith Chintala. 2015. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv:1511.06434 [cs] http://arxiv.org/abs/ 1511.06434. [↗](http://arxiv.org/abs/) [our card](https://md.research.elamur.ai/free/en/papers/radford-2015-unsupervised-representation-learning-deep-convolutional/)
41. Reinhard Rapp. 1999. Automatic Identification of Word Translations from Unrelated English and German Corpora. In ACL. https://doi.org/10.3115/ 1034678.1034756. [find](https://scholar.google.com/scholar?q=Reinhard+Rapp%2E+1999%2E+Automatic+Identification+of+Word+Translations+from+Unrelated+English+and+German+Corpora%2E+In+ACL%2E+https%3A%2F%2Fdoi%2Eorg%2F10%2E3115%2F+1034678%2E1034756%2E) [our card](https://md.research.elamur.ai/free/en/papers/rapp-1999-automatic-identification-word-translations-unrelated/)
42. Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved Techniques for Training GANs. In NIPS. [http://papers.nips.cc/paper/6125-improved-techniques-for-training-gans.pdf](http://papers.nips.cc/paper/6125-improved-techniques-for-training-gans.pdf). [↗](http://papers.nips.cc/paper/6125-improved-techniques-for-training-gans.pdf) [our card](https://md.research.elamur.ai/free/en/papers/salimans-2016-improved-techniques-training-gans/)
43. Tianze Shi, Zhiyuan Liu, Yang Liu, and Maosong Sun. 2015. Learning Cross-lingual Word Embeddings via Matrix Co-factorization. In ACL-IJCNLP. http:/ /aclanthology.info/papers/learning-cross-lingual-word-embeddings-via-matrix-co-factorization. [find](https://scholar.google.com/scholar?q=Tianze+Shi%2C+Zhiyuan+Liu%2C+Yang+Liu%2C+and+Maosong+Sun%2E+2015%2E+Learning+Cross%2Dlingual+Word+Embeddings+via+Matrix+Co%2Dfactorization%2E+In+ACL%2DIJCNLP%2E+http%3A%2F+%2Faclanthology%2Einfo%2Fpapers%2Flearning%2Dcross%2Dlingual%2Dwor)
44. Samuel Smith, David Turban, Steven Hamblin, and Nils Hammerla. 2017. Offline bilingual word vectors, orthogonal transformations and the inverted softmax. In ICLR. http://arxiv.org/abs/1702.03859. [↗](http://arxiv.org/abs/1702.03859) [our card](https://md.research.elamur.ai/free/en/papers/smith-2017-offline-bilingual-word-vectors-orthogonal/)
45. Casper Kaae Sønderby, Jose Caballero, Lucas Theis, Wenzhe Shi, and Ferenc Huszár. 2016. Amortised MAP Inference for Image Super-resolution. arXiv:1610.04490 [cs, stat] http://arxiv.org/abs/ 1610.04490. — [arXiv:1610.04490](https://arxiv.org/abs/1610.04490) [↗](http://arxiv.org/abs/)
46. Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research [http://www.jmlr.org/papers/v15/](http://www.jmlr.org/papers/v15/) srivastava14a.html. [↗](http://www.jmlr.org/papers/v15/)
47. Chao Xing, Dong Wang, Chao Liu, and Yiye Lin. 2015. Normalized Word Embedding and Orthogonal Transform for Bilingual Word Translation. In NAACL-HLT. [http://aclanthology.info/papers/](http://aclanthology.info/papers/) normalized-word-embedding-and-orthogonal-transform-for-bilingual-word-translation. [↗](http://aclanthology.info/papers/) [our card](https://md.research.elamur.ai/free/en/papers/xing-2015-normalized-word-embedding-orthogonal-transform/)
48. Stephanie Strassel and Jennifer Tracey. 2016. LORELEI Language Packs: Data, Tools, and Resources for Technology Development in Low Resource Languages. In LREC. [http://www.lrec-conf.org/proceedings/lrec2016/pdf/1138](http://www.lrec-conf.org/proceedings/lrec2016/pdf/1138) Paper.pdf. [↗](http://www.lrec-conf.org/proceedings/lrec2016/pdf/1138) [our card](https://md.research.elamur.ai/free/en/papers/strassel-2016-lorelei-language-packs-data-tools/)
49. Hyejin Youn, Logan Sutton, Eric Smith, Cristopher Moore, Jon F. Wilkins, Ian Maddieson, William Croft, and Tanmoy Bhattacharya. 2016. On the universal structure of human lexical semantics. Proceedings of the National Academy of Sciences https://doi.org/10.1073/pnas.1520752113. — [doi:10.1073/pnas.1520752113](https://doi.org/10.1073/pnas.1520752113) [↗](https://doi.org/10.1073/pnas.1520752113)
50. Shyam Upadhyay, Manaal Faruqui, Chris Dyer, and Dan Roth. 2016. Cross-lingual Models of Word Embeddings: An Empirical Comparison. In ACL. http:/ /aclanthology.info/papers/cross-lingual-models-of-word-embeddings-an-empirical-comparison. [find](https://scholar.google.com/scholar?q=Shyam+Upadhyay%2C+Manaal+Faruqui%2C+Chris+Dyer%2C+and+Dan+Roth%2E+2016%2E+Cross%2Dlingual+Models+of+Word+Embeddings%3A+An+Empirical+Comparison%2E+In+ACL%2E+http%3A%2F+%2Faclanthology%2Einfo%2Fpapers%2Fcross%2Dlingual%2Dmodels%2Dof%2Dword%2D)
51. Meng Zhang, Yang Liu, Huanbo Luan, Yiqun Liu, and Maosong Sun. 2016a. Inducing Bilingual Lexica From Non-Parallel Data With Earth Mover’s Distance Regularization. In COLING. [http://aclanthology.info/papers/inducing-bilingual-lexica-from-non-parallel-data-with-earth-mover-s-distance-regularization](http://aclanthology.info/papers/inducing-bilingual-lexica-from-non-parallel-data-with-earth-mover-s-distance-regularization). [↗](http://aclanthology.info/papers/inducing-bilingual-lexica-from-non-parallel-data-with-earth-mover-s-distance-regularization)
52. Laurens Van der Maaten, Minmin Chen, Stephen Tyree, and Kilian Weinberger. 2013. Learning with Marginalized Corrupted Features. In ICML. [http://www.jmlr.org/proceedings/papers/](http://www.jmlr.org/proceedings/papers/) v28/vandermaaten13.html. [↗](http://www.jmlr.org/proceedings/papers/)
53. Ivan Vulić and Anna Korhonen. 2016. On the Role of Seed Lexicons in Learning Bilingual Word Embeddings. In ACL. [http://aclanthology.info/](http://aclanthology.info/) papers/on-the-role-of-seed-lexicons-in-learning-bilingual-word-embeddings. [↗](http://aclanthology.info/)
54. Ivan Vulić and Marie-Francine Moens. 2013. Cross-Lingual Semantic Similarity of Words as the Similarity of Their Semantic Word Responses. In NAACL-HLT. [http://aclanthology.info/papers/](http://aclanthology.info/papers/) cross-lingual-semantic-similarity-of-words-as-the-similarity-of-their-semantic-word-responses. [↗](http://aclanthology.info/papers/)
55. Ivan Vulić and Marie-Francine Moens. 2015. Bilingual Word Embeddings from Non-Parallel Document-Aligned Data Applied to Bilingual Lexicon Induction. In ACL-IJCNLP. [http://aclanthology.info/papers/bilingual-word-embeddings-from-non-parallel-document-aligned-data-applied-to-bilingual-lexicon-inductio…](http://aclanthology.info/papers/bilingual-word-embeddings-from-non-parallel-document-aligned-data-applied-to-bilingual-lexicon-inductio…) [↗](http://aclanthology.info/papers/bilingual-word-embeddings-from-non-parallel-document-aligned-data-applied-to-bilingual-lexicon-inductio…)
56. Meng Zhang, Haoruo Peng, Yang Liu, Huanbo Luan, and Maosong Sun. 2017. Bilingual Lexicon Induction From Non-Parallel Data With Minimal Supervision. In AAAI. [http://thunlp.org/˜zm/publications/](http://thunlp.org/˜zm/publications/) aaai2017.pdf. [↗](http://thunlp.org/˜zm/publications/)
57. Yuan Zhang, David Gaddy, Regina Barzilay, and Tommi Jaakkola. 2016b. Ten Pairs to Tag – Multilingual POS Tagging via Coarse Mapping between Embeddings. In NAACL-HLT. [http://aclanthology.info/papers/ten-pairs-to-tag-multilingual-pos-tagging-via-coarse-mapping-between-embeddings](http://aclanthology.info/papers/ten-pairs-to-tag-multilingual-pos-tagging-via-coarse-mapping-between-embeddings). [↗](http://aclanthology.info/papers/ten-pairs-to-tag-multilingual-pos-tagging-via-coarse-mapping-between-embeddings)
58. Will Y. Zou, Richard Socher, Daniel Cer, and Christopher D. Manning. 2013. Bilingual Word Embeddings for Phrase-Based Machine Translation. In EMNLP. [http://aclanthology.info/papers/](http://aclanthology.info/papers/) bilingual-word-embeddings-for-phrase-based-machine-translation. [↗](http://aclanthology.info/papers/) [our card](https://md.research.elamur.ai/free/en/papers/zou-2013-bilingual-word-embeddings-phrase-based/)
59. Ivan Vulić, Wim De Smet, and Marie-Francine Moens. 2011. Identifying Word Translations from Comparable Corpora Using Latent Topic Models. In ACL-HLT. [http://aclanthology.info/papers/](http://aclanthology.info/papers/) identifying-word-translations-from-comparable-corpora-using-latent-topic-models. [↗](http://aclanthology.info/papers/)
60. Stefan Wager, Sida Wang, and Percy S Liang. 2013. Dropout Training as Adaptive Regularization. In NIPS. [http://papers.nips.cc/paper/4882-dropout-training-as-adaptive-regularization.pdf](http://papers.nips.cc/paper/4882-dropout-training-as-adaptive-regularization.pdf). [↗](http://papers.nips.cc/paper/4882-dropout-training-as-adaptive-regularization.pdf)
61. Michael Wick, Pallika Kanani, and Adam Pocock. 2016. Minimally-Constrained Multilingual Embeddings via Artificial Code-Switching. In AAAI. [http://www.aaai.org/Conferences/AAAI/](http://www.aaai.org/Conferences/AAAI/) 2016/Papers/15Wick12464.pdf. [↗](http://www.aaai.org/Conferences/AAAI/)