IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i11p2484-d1157981.html
   My bibliography  Save this article

Reduction of Neural Machine Translation Failures by Incorporating Statistical Machine Translation

Author

Listed:
  • Jani Dugonik

    (Faculty of Electrical Engineering and Computer Science, University of Maribor, SI-2000 Maribor, Slovenia)

  • Mirjam Sepesy Maučec

    (Faculty of Electrical Engineering and Computer Science, University of Maribor, SI-2000 Maribor, Slovenia)

  • Domen Verber

    (Faculty of Electrical Engineering and Computer Science, University of Maribor, SI-2000 Maribor, Slovenia)

  • Janez Brest

    (Faculty of Electrical Engineering and Computer Science, University of Maribor, SI-2000 Maribor, Slovenia)

Abstract

This paper proposes a hybrid machine translation (HMT) system that improves the quality of neural machine translation (NMT) by incorporating statistical machine translation (SMT). Therefore, two NMT systems and two SMT systems were built for the Slovenian–English language pair, each for translation in one direction. We used a multilingual language model to embed the source sentence and translations into the same vector space. From each vector, we extracted features based on the distances and similarities calculated between the source sentence and the NMT translation, and between the source sentence and the SMT translation. To select the best possible translation, we used several well-known classifiers to predict which translation system generated a better translation of the source sentence. The proposed method of combining SMT and NMT in the hybrid system is novel. Our framework is language-independent and can be applied to other languages supported by the multilingual language model. Our experiment involved empirical applications. We compared the performance of the classifiers, and the results demonstrate that our proposed HMT system achieved notable improvements in the BLEU score, with an increase of 1.5 points and 10.9 points for both translation directions, respectively.

Suggested Citation

  • Jani Dugonik & Mirjam Sepesy Maučec & Domen Verber & Janez Brest, 2023. "Reduction of Neural Machine Translation Failures by Incorporating Statistical Machine Translation," Mathematics, MDPI, vol. 11(11), pages 1-22, May.
    • Handle: RePEc:gam:jmathe:v:11:y:2023:i:11:p:2484-:d:1157981
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/11/2484/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/11/11/2484/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Ranjit Panigrahi & Samarjeet Borah & Akash Kumar Bhoi & Muhammad Fazal Ijaz & Moumita Pramanik & Yogesh Kumar & Rutvij H. Jhaveri, 2021. "A Consolidated Decision Tree-Based Intrusion Detection System for Binary and Multiclass Imbalanced Datasets," Mathematics, MDPI, vol. 9(7), pages 1-35, March.
    2. Nebojsa Bacanin & Miodrag Zivkovic & Catalin Stoean & Milos Antonijevic & Stefana Janicijevic & Marko Sarac & Ivana Strumberger, 2022. "Application of Natural Language Processing and Machine Learning Boosted with Swarm Intelligence for Spam Email Filtering," Mathematics, MDPI, vol. 10(22), pages 1-31, November.
    3. Nikolai Krivulin & Alexey Prinkov & Igor Gladkikh, 2022. "Using Pairwise Comparisons to Determine Consumer Preferences in Hotel Selection," Mathematics, MDPI, vol. 10(5), pages 1-25, February.
    4. Anas Alokla & Walaa Gad & Waleed Nazih & Mustafa Aref & Abdel-Badeeh Salem, 2022. "Retrieval-Based Transformer Pseudocode Generation," Mathematics, MDPI, vol. 10(4), pages 1-16, February.
    5. Edoardo Savini & Cornelia Caragea, 2022. "Intermediate-Task Transfer Learning with BERT for Sarcasm Detection," Mathematics, MDPI, vol. 10(5), pages 1-14, March.
    6. Bi-Min Hsu, 2020. "Comparison of Supervised Classification Models on Textual Data," Mathematics, MDPI, vol. 8(5), pages 1-16, May.
    7. Shengfeng Gan & Shiqi Shao & Long Chen & Liangjun Yu & Liangxiao Jiang, 2021. "Adapting Hidden Naive Bayes for Text Classification," Mathematics, MDPI, vol. 9(19), pages 1-14, September.
    8. Ganesh Dash & Chetan Sharma & Shamneesh Sharma, 2023. "Sustainable Marketing and the Role of Social Media: An Experimental Study Using Natural Language Processing (NLP)," Sustainability, MDPI, vol. 15(6), pages 1-16, March.
    9. Laith H. Baniata & Sangwoo Kang & Isaac. K. E. Ampomah, 2022. "A Reverse Positional Encoding Multi-Head Attention-Based Neural Machine Translation Model for Arabic Dialects," Mathematics, MDPI, vol. 10(19), pages 1-25, October.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Asuamah Yeboah, Samuel, 2023. "Sustaining Change: Unravelling the Socio-cultural Threads of Sustainable Consumption," MPRA Paper 117981, University Library of Munich, Germany, revised 10 Jun 2023.
    2. Florentina Hristea & Cornelia Caragea, 2022. "Preface to the Special Issue “Natural Language Processing (NLP) and Machine Learning (ML)—Theory and Applications”," Mathematics, MDPI, vol. 10(14), pages 1-5, July.
    3. Dušan S. Radivojević & Ivan M. Lazović & Nikola S. Mirkov & Uzahir R. Ramadani & Dušan P. Nikezić, 2023. "A Comparative Evaluation of Self-Attention Mechanism with ConvLSTM Model for Global Aerosol Time Series Forecasting," Mathematics, MDPI, vol. 11(7), pages 1-13, April.
    4. Yongbo Pan & Xunlin Zhu, 2022. "Application of HMM and Ensemble Learning in Intelligent Tunneling," Mathematics, MDPI, vol. 10(10), pages 1-17, May.
    5. Robert Waszkowski & Grzegorz Bocewicz, 2022. "Visibility Matrix: Efficient User Interface Modelling for Low-Code Development Platforms," Sustainability, MDPI, vol. 14(13), pages 1-24, July.
    6. Lefa Zhao & Yafei Zhu & Tianyu Zhao, 2022. "Deep Learning-Based Remaining Useful Life Prediction Method with Transformer Module and Random Forest," Mathematics, MDPI, vol. 10(16), pages 1-15, August.
    7. Miao Jiang & Xin Zhang & Chonghao Chen & Taihua Shao & Honghui Chen, 2022. "Leveraging Part-of-Speech Tagging Features and a Novel Regularization Strategy for Chinese Medical Named Entity Recognition," Mathematics, MDPI, vol. 10(9), pages 1-20, April.
    8. Lu Jiang & Xinyu Kang & Shan Huang & Bo Yang, 2022. "A refinement strategy for identification of scientific software from bioinformatics publications," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(6), pages 3293-3316, June.
    9. O-Jong Kim & Changdon Kee, 2023. "Wavelet and Neural Network-Based Multipath Detection for Precise Positioning Systems," Mathematics, MDPI, vol. 11(6), pages 1-22, March.
    10. Tahir Mehmood & Ivan Serina & Alberto Lavelli & Luca Putelli & Alfonso Gerevini, 2023. "On the Use of Knowledge Transfer Techniques for Biomedical Named Entity Recognition," Future Internet, MDPI, vol. 15(2), pages 1-27, February.
    11. P. Chellammal & Sheba Kezia Malarchelvi & K. Reka & G. Raja, 2022. "Fast and Effective Intrusion Detection Using Multi-Layered Deep Learning Networks," International Journal of Web Services Research (IJWSR), IGI Global, vol. 19(1), pages 1-16, January.
    12. Hojat Behrooz & Carlo Lipizzi & George Korfiatis & Mohammad Ilbeigi & Martin Powell & Mina Nouri, 2023. "Towards Automating the Identification of Sustainable Projects Seeking Financial Support: An AI-Powered Approach," Sustainability, MDPI, vol. 15(12), pages 1-12, June.
    13. Abdulilah Mohammad Mayet & Seyed Mehdi Alizadeh & Zana Azeez Kakarash & Ali Awadh Al-Qahtani & Abdullah K. Alanazi & Hala H. Alhashimi & Ehsan Eftekhari-Zadeh & Ehsan Nazemi, 2022. "Introducing a Precise System for Determining Volume Percentages Independent of Scale Thickness and Type of Flow Regime," Mathematics, MDPI, vol. 10(10), pages 1-13, May.
    14. Anas Alokla & Walaa Gad & Waleed Nazih & Mustafa Aref & Abdel-badeeh Salem, 2022. "Pseudocode Generation from Source Code Using the BART Model," Mathematics, MDPI, vol. 10(21), pages 1-14, October.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:11:y:2023:i:11:p:2484-:d:1157981. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.