skip to main content
short-paper

Exploiting Japanese–Chinese Cognates with Shared Private Representations for NMT

Published:25 November 2022Publication History
Skip Abstract Section

Abstract

Neural machine translation has achieved remarkable progress over the past several years; however, little attention has been paid to machine translation (MT) between Japanese and Chinese, which share a large proportion of cognate words that can be utilized as additional linguistic knowledge to enhance translation performance. In this article, we seek to strengthen the semantic correlation between Japanese and Chinese by leveraging cognate words that share common Chinese characters. Specifically, we experiment with three strategies: (1) a shared vocabulary with cognate lexicon induction, which models the commonality between source and target cognates; (2) a shared private representation with a dynamic gating mechanism, which models the language-specific features on the source side; and (3) an embedding shortcut, which enables the decoder to access the shared private representation with shortest distance and aids the training process. The experiments and analysis presented in this article demonstrate that our proposed approaches can significantly improve the performance of both Japanese-to-Chinese and Chinese-to-Japanese translations and verify the effectiveness of exploiting Japanese–Chinese cognates for MT.

REFERENCES

  1. [1] Bahdanau Dzmitry, Cho Kyunghyun, and Bengio Yoshua. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of the International Conference on Learning Representations (ICLR’15).Google ScholarGoogle Scholar
  2. [2] Chen Mia Xu, Firat Orhan, Bapna Ankur, Johnson Melvin, Macherey Wolfgang, Foster George F., Jones Llion, Parmar Niki, Schuster Mike, Chen Zhifeng, Wu Yonghui, and Hughes Macduff. 2018. The best of both worlds: Combining recent advances in neural machine translation. CoRR abs/1804.09849 (2018).Google ScholarGoogle Scholar
  3. [3] Chu Chenhui, Nakazawa Toshiaki, Kawahara Daisuke, and Kurohashi Sadao. 2013. Chinese-japanese machine translation exploiting chinese characters. ACM Trans. As. Lang. Inf. Process. 12, 4 (2013), 16:1–16:25.Google ScholarGoogle Scholar
  4. [4] Chu Chenhui, Nakazawa Toshiaki, and Kurohashi Sadao. 2012. Chinese characters mapping table of japanese, traditional chinese and simplified chinese. In Proceedings of the International Conference on Language Resources and Evaluation (LREC’12). 21492152.Google ScholarGoogle Scholar
  5. [5] Dabre Raj, Chu Chenhui, and Kunchukuttan Anoop. 2020. A comprehensive survey of multilingual neural machine translation. CoRR abs/2001.01115 (2020).Google ScholarGoogle Scholar
  6. [6] Dhall Sakshi, Dwivedi Ashutosh Dhar, Pal Saibal K., and Srivastava Gautam. 2022. Blockchain-based framework for reducing fake or vicious news spread on social media/messaging platforms. ACM Trans. As. Low Resour. Lang. Inf. Process. 21, 1 (2022), 8:1–8:13.Google ScholarGoogle Scholar
  7. [7] Emelin Denis, Titov Ivan, and Sennrich Rico. 2019. Widening the representation bottleneck in neural machine translation with lexical shortcuts. In Proceedings of the Conference on Machine Translation. 102115.Google ScholarGoogle ScholarCross RefCross Ref
  8. [8] Gehring Jonas, Auli Michael, Grangier David, Yarats Denis, and Dauphin Yann N.. 2017. Convolutional sequence to sequence learning. In Proceedings of the International Conference on Machine Learning (ICML’17). 12431252.Google ScholarGoogle Scholar
  9. [9] Klein Guillaume, Kim Yoon, Deng Yuntian, Senellart Jean, and Rush Alexander M.. 2017. OpenNMT: Open-source toolkit for neural machine translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL’17). 6772.Google ScholarGoogle ScholarCross RefCross Ref
  10. [10] Kuang Shaohui, Li Junhui, Branco António, Luo Weihua, and Xiong Deyi. 2018. Attention focusing for neural machine translation by bridging source and target embeddings. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL’18). Melbourne, Australia, 17671776.Google ScholarGoogle ScholarCross RefCross Ref
  11. [11] Kurosawa Michiki, Matsumura Yukio, Yamagishi Hayahide, and Komachi Mamoru. 2018. Japanese predicate conjugation for neural machine translation. CoRR abs/1805.10047 (2018).Google ScholarGoogle Scholar
  12. [12] Lee Chen-Yu, Xie Saining, Gallagher Patrick W., Zhang Zhengyou, and Tu Zhuowen. 2014. Deeply-supervised nets. CoRR abs/1409.5185 (2014).Google ScholarGoogle Scholar
  13. [13] Liu Xuebo, Wong Derek F., Liu Yang, Chao Lidia S., Xiao Tong, and Zhu Jingbo. 2019. Shared-private bilingual word embeddings for neural machine translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL’19). 36133622.Google ScholarGoogle ScholarCross RefCross Ref
  14. [14] Nakazawa Toshiaki, Yaguchi Manabu, Uchimoto Kiyotaka, Utiyama Masao, Sumita Eiichiro, Kurohashi Sadao, and Isahara Hitoshi. 2016. ASPEC: Asian scientific paper excerpt corpus. In Proceedings of International Conference on Language Resources and Evaluation (LREC’16).Google ScholarGoogle Scholar
  15. [15] Palanivinayagam Ashokkumar, Shankar G. Siva, Srivastava Gautam, Maddikunta Praveen Kumar Reddy, and Gadekallu Thippa Reddy. 2021. A two-stage text feature selection algorithm for improving text classification. ACM Trans. As. Low Resour. Lang. Inf. Process. 20, 3 (2021), 49:1–49:19.Google ScholarGoogle Scholar
  16. [16] Papineni Kishore, Roukos Salim, Ward Todd, and Zhu Wei-Jing. 2002. BLEU: A method for automatic evaluation of machine translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL’02). 311318.Google ScholarGoogle Scholar
  17. [17] Park Jeonghyeok and Zhao Hai. 2019. Korean-to-chinese machine translation using chinese character as pivot clue. CoRR abs/1911.11008 (2019).Google ScholarGoogle Scholar
  18. [18] Sennrich Rico, Haddow Barry, and Birch Alexandra. 2016. Neural machine translation of rare words with subword units. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL’16). 17151725.Google ScholarGoogle ScholarCross RefCross Ref
  19. [19] Srivastava Rupesh Kumar, Greff Klaus, and Schmidhuber Jürgen. 2015. Highway networks. CoRR abs/1505.00387 (2015).Google ScholarGoogle Scholar
  20. [20] Sutskever Ilya, Vinyals Oriol, and Le Quoc V.. 2014. Sequence to sequence learning with neural networks. In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS’14). 31043112.Google ScholarGoogle Scholar
  21. [21] Vaswani Ashish, Shazeer Noam, Parmar Niki, Uszkoreit Jakob, Jones Llion, Gomez Aidan N., Kaiser Lukasz, and Polosukhin Illia. 2017. Attention is all you need. In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS’17). 59986008.Google ScholarGoogle Scholar
  22. [22] Wang Changhan, Cho Kyunghyun, and Gu Jiatao. 2020. Neural machine translation with byte-level subwords. In Proceedings of the Annual AAAI Conference on Artificial Intelligence (AAAI’20). New York, NY, 91549160.Google ScholarGoogle ScholarCross RefCross Ref
  23. [23] Wang Jilei, Luo Shiying, Shi Weiyan, Dai Tao, and Xia Shu-Tao. 2018. Exploiting common characters in chinese and japanese to learn cross-lingual word embeddings via matrix factorization. In Proceedings of the 3rd Workshop on Representation Learning for NLP @ACL. 113121.Google ScholarGoogle ScholarCross RefCross Ref
  24. [24] Wang Rui, Zhao Hai, Ploux Sabine, Lu Bao-Liang, Utiyama Masao, and Sumita Eiichiro. 2018. Graph-based bilingual word embedding for statistical machine translation. ACM Trans. As. Low Resour. Lang. Inf. Process. 17, 4 (October2018), 31:1–31:23.Google ScholarGoogle Scholar
  25. [25] Wu Lijun, Tian Fei, Zhao Li, Lai Jianhuang, and Liu TieYan. 2018. Word attention for sequence to sequence text understanding. In Proceedings of the 32th Conference on Artificial Intelligence. 55785585.Google ScholarGoogle ScholarCross RefCross Ref
  26. [26] Zhang Longtu and Komachi Mamoru. 2021. Using sub-character level information for neural machine translation of logographic languages. ACM Trans. As. Low Resour. Lang. Inf. Process. 20, 2 (2021), 31:1–31:15.Google ScholarGoogle Scholar

Index Terms

  1. Exploiting Japanese–Chinese Cognates with Shared Private Representations for NMT

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      • Published in

        cover image ACM Transactions on Asian and Low-Resource Language Information Processing
        ACM Transactions on Asian and Low-Resource Language Information Processing  Volume 22, Issue 1
        January 2023
        340 pages
        ISSN:2375-4699
        EISSN:2375-4702
        DOI:10.1145/3572718
        Issue’s Table of Contents

        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 25 November 2022
        • Online AM: 5 May 2022
        • Accepted: 24 April 2022
        • Revised: 6 April 2022
        • Received: 31 October 2021
        Published in tallip Volume 22, Issue 1

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • short-paper
        • Refereed
      • Article Metrics

        • Downloads (Last 12 months)119
        • Downloads (Last 6 weeks)8

        Other Metrics

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Full Text

      View this article in Full Text.

      View Full Text

      HTML Format

      View this article in HTML Format .

      View HTML Format
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!