Skip to main content
SpringerLink
Log in

Word Embeddings at Post-Editing

  • Conference paper
  • First Online:
Computational Processing of the Portuguese Language (PROPOR 2020)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 12037))

  • 539 Accesses

Abstract

After more than 60 years of research in Machine Translation, it has not been possible yet to develop a perfect fully automatic translation system for unlimited purposes. Thus, it is still necessary post-editing to correct possible mistranslations output by the Machine Translation system. Several approaches have been proposed in order to also automate the post-editing task. This work addresses one of the main steps of an automatic post-editing tool: the automatic proposition of word replacements for a Machine Translation output. To do so, we propose a novel method based on bilingual word embeddings. In the experiments present in this paper we show the effectiveness of this approach in two of the most frequent lexical errors: ‘not translated word’ and ‘incorrectly translated word’.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    The baseline NMT system was trained using the OpenNMT [13] tool and the FAPESP corpus [2]. The test corpus is composed of 300 sentences from FAPESP’s test-a and 100 sentences from FAPESP’s test-b, which were manually annotated using the BLAST [26].

  2. 2.

    The bilingual space used in our experiments was trained by MUSE [8] from the Wikipedia corpus and made available by the authors under https://github.com/facebookresearch/MUSE.

  3. 3.

    We have also implemented step 1 but due to space limitations it will not be presented in this paper. Further information about this step can be found at [11].

  4. 4.

    Available at http://www.lalic.dc.ufscar.br/portal/.

  5. 5.

    Available at: https://github.com/lalic-ufscar/we-pe-tool.

  6. 6.

    The BLEU scores were calculated using the Moses toolkit (https://github.com/moses-smt/mosesdecoder/blob/master/scripts/generic/mteval-v14.pl) taking into account only those sentences annotated with this specific error.

References

  1. Armentano-Oller, C., et al.: Open-source Portuguese–Spanish machine translation. In: Vieira, R., Quaresma, P., Nunes, M.G.V., Mamede, N.J., Oliveira, C., Dias, M.C. (eds.) PROPOR 2006. LNCS (LNAI), vol. 3960, pp. 50–59. Springer, Heidelberg (2006). https://doi.org/10.1007/11751984_6

    Chapter  Google Scholar 

  2. Aziz, W., Specia, L.: Fully automatic compilation of a Portuguese-English parallel corpus for statistical machine translation. In: STIL 2011, Cuiabá, MT, Outubro 2011

    Google Scholar 

  3. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015). http://arxiv.org/abs/1409.0473

  4. Béchara, H., Rubino, R., He, Y., Ma, Y., Genabith, J.: An evaluation of statistical post-editing systems applied to RBMT and SMT systems. In: Proceedings of COLING 2012, pp. 215–230. The COLING 2012 Organizing Committee (2012). http://aclweb.org/anthology/C12-1014

  5. Bérard, A., Servan, C., Pietquin, O., Besacier, L.: MultiVec: a multilingual and multilevel representation learning toolkit for NLP. In: The 10th Edition of the Language Resources and Evaluation Conference (LREC 2016), May 2016

    Google Scholar 

  6. Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135–146 (2017). https://doi.org/10.1162/tacl_a_00051. https://www.aclweb.org/anthology/Q17-1010

    Article  Google Scholar 

  7. Caseli, H.M.: Indução de léxicos bilíngües e regras para a tradução automática. Ph.D. thesis, ICMC-USP, May 2007

    Google Scholar 

  8. Conneau, A., Lample, G., Ranzato, M., Denoyer, L., Jégou, H.: Word translation without parallel data. In: Proceedings of the Sixth International Conference on Learning Representations, May 2018

    Google Scholar 

  9. Elming, J.: Transformation-based correction of rule-based MT. In: Proceedings of EAMT, pp. 219–226 (2006)

    Google Scholar 

  10. Harris, Z.S.: Distributional structure. Word 10(2–3), 146–162 (1954)

    Article  Google Scholar 

  11. Inácio, M.L.: Pós-edição automática e semanticamente motivada de traduções em português do Brasil. Monografia de Trabalho de Conclusão de Curso de Graduação em Ciência da Computação, UFSCar (Universidade Federal de São Carlos), São Carlos, Brasil (2018). 93 p. http://www.lalic.dc.ufscar.br

  12. Junczys-Dowmunt, M., Grundkiewicz, R.: An exploration of neural sequence-to-sequence architectures for automatic post-editing. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 120–129. Asian Federation of Natural Language Processing (2017). http://aclweb.org/anthology/I17-1013

  13. Klein, G., Kim, Y., Deng, Y., Senellart, J., Rush, A.: OpenNMT: open-source toolkit for neural machine translation. In: Proceedings of ACL 2017, System Demonstrations, pp. 67–72. Association for Computational Linguistics (2017). http://aclweb.org/anthology/P17-4012

  14. Koehn, P., et al.: Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, ACL 2007, pp. 177–180. Association for Computational Linguistics, Stroudsburg (2007). http://dl.acm.org/citation.cfm?id=1557769.1557821

  15. Lagarda, A.L., Alabau, V., Casacuberta, F., Silva, R., Díaz-de Liaño, E.: Statistical post-editing of a rule-based machine translation system. In: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, pp. 217–220. Association for Computational Linguistics (2009). http://aclweb.org/anthology/N09-2055

  16. Mareček, D., Rosa, R., Galuščáková, P., Bojar, O.: Two-step translation with grammatical post-processing. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 426–432. Association for Computational Linguistics (2011)

    Google Scholar 

  17. Martins, D.B.J., Caseli, H.M.: Automatic machine translation error identification. Mach. Transl. 29(1), 1–24 (2015). https://doi.org/10.1007/s10590-014-9163-y

    Article  Google Scholar 

  18. Martins, D.B.J.: Pós-edição automática de textos traduzidos automaticamente de inglês para português do Brasil. Master’s thesis, PPG-CC-UFSCar, February 2014. https://repositorio.ufscar.br/bitstream/handle/ufscar/563/5932.pdf

  19. Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. CoRR abs/1310.4546 (2013). http://arxiv.org/abs/1310.4546

  20. Och, F.J., Ney, H.: The alignment template approach to statistical machine translation. Comput. Linguist. 30(4), 417–449 (2004). https://doi.org/10.1162/0891201042544884

    Article  MATH  Google Scholar 

  21. Pal, S., Naskar, S.K., Vela, M., van Genabith, J.: A neural network based approach to automatic post-editing. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), vol. 2, pp. 281–286 (2016)

    Google Scholar 

  22. Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics (2002)

    Google Scholar 

  23. Popović, M.: Language-related issues for NMT and PBMT for English–German and English–Serbian. Mach. Transl. (2018). https://doi.org/10.1007/s10590-018-9219-5

    Article  Google Scholar 

  24. Silva, J.R., Caseli, H.M.: Generating sense embeddings for syntactic and semantic analogy for Portuguese. In: Proceedings of the XII Symposium in Information and Human Language Technology and Collocates Events, Salvador, BA, 15–18 October 2019, pp. 104–113 (2019). http://comissoes.sbc.org.br/ce-pln/stil2019/proceedings-stil-2019-Final.pdf, (Best Paper)

  25. Simard, M., Goutte, C., Isabelle, P.: Statistical phrase-based post-editing. In: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pp. 508–515. Association for Computational Linguistics (2007). http://aclweb.org/anthology/N07-1064

  26. Stymne, S.: Blast: a tool for error analysis of machine translation output. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Systems Demonstrations, pp. 56–61. Association for Computational Linguistics (2011)

    Google Scholar 

Download references

Acknowledgements

This work has been developed with the support from São Paulo Research Foundation (FAPESP), grants #2016/21317-0 (Undergraduate research grant) and #2016/13002-0 (MMeaning Project).

Author information

Authors and Affiliations

  1. NILC - Interinstitutional Center for Computational Linguistics Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo, São Carlos, SP, 13566-590, Brazil

    Marcio Lima Inácio & Helena de Medeiros Caseli

  2. LALIC - Laboratório de Linguística e Inteligência Computacional Departamento de Computação, Universidade Federal de São Carlos, São Carlos, SP, 13565-905, Brazil

    Helena de Medeiros Caseli

Authors
  1. Marcio Lima Inácio
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Helena de Medeiros Caseli
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marcio Lima Inácio .

Editor information

Editors and Affiliations

  1. University of Évora, Evora, Portugal

    Paulo Quaresma

  2. University of Évora, Evora, Portugal

    Renata Vieira

  3. University of São Paulo, São Carlos, Brazil

    Sandra Aluísio

  4. University of Lisbon, Lisbon, Portugal

    Helena Moniz

  5. INESC-ID/ISCTE-IUL, Lisbon, Portugal

    Fernando Batista

  6. University of Évora, Evora, Portugal

    Teresa Gonçalves

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Inácio, M.L., de Medeiros Caseli, H. (2020). Word Embeddings at Post-Editing. In: Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., Gonçalves, T. (eds) Computational Processing of the Portuguese Language. PROPOR 2020. Lecture Notes in Computer Science(), vol 12037. Springer, Cham. https://doi.org/10.1007/978-3-030-41505-1_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-41505-1_31

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-41504-4

  • Online ISBN: 978-3-030-41505-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation