Top

Published in:

2018 | OriginalPaper | Chapter

Word and Phrase Dictionaries Generated with Multiple Translation Paths

Authors : Jouko Vankka, Christoffer Aminoff, Dmitriy Haralson, Janne Siipola

Published in: Information and Software Technologies

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

Methods used to learn bilingual word embedding mappings, which project the source-language embeddings into the target embedding space, are compared in this paper. Orthogonal transformations, which are robust to noise, can learn to translate between word pairs they have never seen during training (zero-shot translation). Using multiple translation paths, e.g. Finnish \(\rightarrow \) English \(\rightarrow \) Russian and Finnish \(\rightarrow \) French \(\rightarrow \) Russian, at the same time and combining the results was found to improve the results of this process. Four new methods are presented for the calculation of either the single most similar or the five most similar words, based on the results of multiple translation paths. Of these, the Summation method was found to improve the P@1 translation precision by 1.6% points compared to the best result obtained with a direct translation (Fi \(\rightarrow \) Ru). The probability margin is presented as a confidence score. With similar coverages, the probability margin was found to outperform probability as a confidence score in terms of P@1 and P@5.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

previous chapter Experience with Distance Learning of Informatics

next chapter Sentiment Analysis of Lithuanian Texts Using Deep Learning Methods

Aller Media Oy: The Suomi 24 Corpus (2014). http://urn.fi/urn:nbn:fi:lb-201412171. 14 May 2015 Version

Amazon S3: Swedish Wikipedia (2017). https://s3-us-west-1.amazonaws.com/fasttext-vectors/wiki.sv.vec

Ammar, W., Mulcaire, G., Tsvetkov, Y., Lample, G., Dyer, C., Smith, N.A.: Massively multilingual word embeddings. CoRR abs/1602.01925 (2016). http://arxiv.org/abs/1602.01925

Artetxe, M., Labaka, G., Agirre, E.: Learning principled bilingual mappings of word embeddings while preserving monolingual invariance. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2289–2294 (2016)

Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. arXiv preprint arXiv:1607.04606 (2016)

Dinu, G., Baroni, M.: Improving zero-shot learning by mitigating the hubness problem. CoRR abs/1412.6568 (2014). http://arxiv.org/abs/1412.6568

Faruqui, M., Dyer, C.: Improving vector space word representations using multilingual correlation. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, pp. 462–471 (2014)

Haghighi, A., Liang, P., Berg-Kirkpatrick, T., Klein, D.: Learning bilingual lexicons from monolingual corpora, pp. 771–779 (2008)

Jansen, S.: Word and phrase translation with word2vec. CoRR abs/1705.03127 (2017). http://arxiv.org/abs/1705.03127

10.

Johnson, M., et al.: Google’s multilingual neural machine translation system: enabling zero-shot translation. CoRR abs/1611.04558 (2016). http://arxiv.org/abs/1611.04558

11.

Koehn, P., Knight, K.: Estimating word translation probabilities from unrelated monolingual corpora using the em algorithm. In: Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence, pp. 711–715. AAAI Press (2000). http://dl.acm.org/citation.cfm?id=647288.721610

12.

Koehn, P., Knight, K.: Learning a translation lexicon from monolingual corpora. In: Proceedings of the ACL-02 Workshop on Unsupervised Lexical Acquisition, vol. 9, pp. 9–16. Association for Computational Linguistics (2002)

13.

Kyubyong/wordvectors: French Wikipedia (2017). https://github.com/Kyubyong/wordvectors

14.

Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)

15.

Mikolov, T., Le, Q.V., Sutskever, I.: Exploiting similarities among languages for machine translation. CoRR abs/1309.4168 (2013). http://arxiv.org/abs/1309.4168

16.

Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)

17.

mmihaltz/word2vec-GoogleNews-vectors: GoogleNews (2017). https://github.com/mmihaltz/word2vec-GoogleNews-vectors

18.

Rapp, R.: Automatic identification of word translations from unrelated English and German corpora. In: Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics on Computational Linguistics, pp. 519–526. Association for Computational Linguistics (1999)

19.

Ruder, S.: A survey of cross-lingual embedding models. CoRR abs/1706.04902 (2017). http://arxiv.org/abs/1706.04902

20.

RusVectōrēs: word embeddings for Russian online: Russian National Corpus + Russian Wikipedia (2017). http://rusvectores.org/static/models/ruwikiruscorpora_upos_cbow_300_20_2017.bin.gz

21.

Schwenk, H., Tran, K., Firat, O., Douze, M.: Learning joint multilingual sentence representations with neural machine translation. CoRR abs/1704.04154 (2017). http://arxiv.org/abs/1704.04154

22.

Smith, S.L., Turban, D.H.P., Hamblin, S., Hammerla, N.Y.: Offline bilingual word vectors, orthogonal transformations and the inverted softmax. CoRR abs/1702.03859 (2017). http://arxiv.org/abs/1702.03859

23.

Venekoski, V.: Semantics in Finnish Distributional Language Models. Master’s thesis, University of Helsinki (2016)

24.

Vulic, I., Korhonen, A.: On the role of seed lexicons in learning bilingual word embeddings. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (2016). http://aclweb.org/anthology/P/P16/P16-1024.pdf

25.

Xing, C., Wang, D., Liu, C., Lin, Y.: Normalized word embedding and orthogonal transform for bilingual word translation. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1006–1011 (2015)

Title: Word and Phrase Dictionaries Generated with Multiple Translation Paths
Authors: Jouko Vankka
Christoffer Aminoff
Dmitriy Haralson
Janne Siipola
Publisher: Springer International Publishing
Book: Information and Software Technologies
Print ISBN: 978-3-319-99971-5

Electronic ISBN: 978-3-319-99972-2

Copyright Year: 2018
DOI: https://doi.org/10.1007/978-3-319-99972-2_42

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner