Machine Translation Utilizing Similar Translation Retrieval | SpringerLink
Skip to main content
Springer Nature Link
Log in

Machine Translation Utilizing Similar Translation Retrieval

  • Conference paper
  • First Online:
Advances in Artificial Intelligence (JSAI 2021)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1423))

Included in the following conference series:

  • 433 Accesses

Abstract

Neural Fuzzy Repair (NFR) system enables an NMT system to improve translation accuracy using similar translations searched from Translation Memory. This paper compared edit distance and sentence-BERT (SBERT) as the similarity measures used in the search for similar translations, and showed that SBERT outperformed edit distance in the case of small corpus sizes. This paper also studied a method to automatically select the most appropriate translation from more than one candidates. Compared to the naive method based on the number of tokens, the method based on the inner product of SBERT’s sentence embedding achieved significant improvements. These results prove the effectiveness of the SBERT-based approach in the NFR system.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 20591
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 25739
Price includes VAT (Japan)
  • 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

Similar content being viewed by others

Notes

  1. 1.

    http://opus.nlpl.eu/ECB.php.

  2. 2.

    https://github.com/UKPLab/sentence-transformers.

  3. 3.

    Except for the case of the perfect match with \(t_i\) (\(t' \not = t_i\)). In the case of the edit distance as the similarity measure, we follow the condition of \(sim(s_i,(s',t')) > lbd=0\) when the lower bound as \(lbd=0\).

  4. 4.

    In the evaluation of this paper, the ratio \(k=1.18\) measured from the ECB corpus [8] is used.

  5. 5.

    https://github.com/OpenNMT/OpenNMT-py.

  6. 6.

    https://github.com/moses-smt/mosesdecoder.

  7. 7.

    https://github.com/rsennrich/subword-nmt.

  8. 8.

    multi-bleu.perl.

  9. 9.

    https://github.com/odashi/mteval.

References

  1. Bulte, B., Tezcan, A.: Neural fuzzy repair: integrating fuzzy matches into neural machine translation. In: Proceedings of 57th ACL, pp. 1800–1809 (2019)

    Google Scholar 

  2. Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional Transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)

    Google Scholar 

  3. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of 3rd ICLR (2015)

    Google Scholar 

  4. Koehn, P., et al.: Moses: open source toolkit for statistical machine translation. In: Proceedings of 45th ACL, pp. 177–180 (2007)

    Google Scholar 

  5. Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of EMNLP and 9th IJCNLP, pp. 3982–3992 (2019)

    Google Scholar 

  6. Reimers, N., Gurevych, I.: Making monolingual sentence embeddings multilingual using knowledge distillation. In: Proceedings of EMNLP, pp. 4512–4525 (2020)

    Google Scholar 

  7. Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of 54th ACL, pp. 1715–1725 (2016)

    Google Scholar 

  8. Tiedemann, J.: Parallel data, tools and interfaces in OPUS. In: Proceedings of 8th LREC, pp. 2214–2218 (2012)

    Google Scholar 

  9. Vanallemeersch, T., Vandeghinste, V.: Assessing linguistically aware fuzzy matching in translation memories. In: Proceedings of 18th EAMT, pp. 153–160 (2015)

    Google Scholar 

  10. Vaswani, A., et al.: Attention is all you need. In: Proceedings of 30th NIPS, pp. 5998–6008 (2017)

    Google Scholar 

  11. Xu, J., Crego, J., Senellart, J.: Boosting neural machine translation with similar translations. In: Proceedings of 58th ACL, pp. 1580–1590 (2020)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Graduate School of Science and Technology, University of Tsukuba, 1-1-1, Tennodai, Tsukuba, Ibaraki, 305-8573, Japan

    Takuya Tamura, Yizhen Wei & Takehito Utsuro

  2. NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, “Keihanna Science City”, Kyoto, 619-0237, Japan

    Masaaki Nagata

Authors
  1. Takuya Tamura
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yizhen Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Takehito Utsuro
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Masaaki Nagata
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Takehito Utsuro .

Editor information

Editors and Affiliations

  1. Graduate School of System Design, Tokyo Metropolitan University, Hino, Tokyo, Japan

    Yasufumi Takama

  2. Graduate School of Economics, Osaka University, Toyonaka, Osaka, Japan

    Naohiro Matsumura

  3. Faculty of Business and Commerce, Kansai University, Osaka, Japan

    Katsutoshi Yada

  4. Faculty of Informatics, Kansai University, Takatsuki, Osaka, Japan

    Mitsunori Matsushita

  5. Department of Applied Computer Science, Tokyo Polytechnic University, Atsugi, Kanagawa, Japan

    Daisuke Katagami

  6. Division of Behavioral Science, Chiba University, Chiba, Japan

    Akinori Abe

  7. Department of Intelligence Science and Technology, Kyoto University, Kyoto, Japan

    Hisashi Kashima

  8. Institute of Industrial Science, The University of Tokyo, Meguro-ku, Tokyo, Japan

    Toshihiro Hiraoka

  9. Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan

    Takahiro Uchiya

  10. Graduate School of Information Science and Technology Sapporo Hokkaido Japan, Hokkaido University, Sapporo, Hokkaido, Japan

    Rafal Rzepka

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Tamura, T., Wei, Y., Utsuro, T., Nagata, M. (2022). Machine Translation Utilizing Similar Translation Retrieval. In: Takama, Y., et al. Advances in Artificial Intelligence. JSAI 2021. Advances in Intelligent Systems and Computing, vol 1423. Springer, Cham. https://doi.org/10.1007/978-3-030-96451-1_4

Download citation

Publish with us

Policies and ethics

Search

Navigation