Skip to main content
SpringerLink
Log in

A fuzzy model for NMT word alignment using quasi-perfect matching

  • Published:
Computational and Applied Mathematics Aims and scope Submit manuscript

Abstract

In this article, first, the concept of quasi-perfect matching in a fuzzy graph is introduced. In addition to using these types of matching in expressing our main application goal, this introduction provides a complete classification on all matching that are known as “maximum matching” in classical graph theory. A useful set called conductive set has been obtained to be able to customize any of the introduced categories for matchings as desired or according to the practical necessity. Extensions with different powers are made from a fuzzy graph and useful meters are generated on each of them. These extensions and related concepts have been used in a different approach for words alignment in machine translation. The mismatch between the number of sentence words in the source and target languages has always been a challenge for the designers of machine translation systems in word-based alignment. To solve this, we introduce a different approach for aligning words, based on a fuzzy graph extracted from a parallel corpus.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Data Availability

The authors declare that the data supporting the findings of this study are available within the paper, its supplementary information files

Notes

  1. The number of elements in the set \(E_{s}(M)\)

  2. \(G^*\setminus S\) means subtracting S from \(G^*\).

  3. [ ] represents the smallest integer operation.

References

  • Akram M (2011) Bipolar fuzzy graphs. Inf Sci 181:5548–5564

    Article  MathSciNet  MATH  Google Scholar 

  • Bondy JA, Murty USR (2008) Graph theory with applications. Springer, London

    MATH  Google Scholar 

  • Borzooei RA, Almallah R, Jun YB, Ghaznavi H (2020) Inverse fuzzy graphs with applications. New Math Nat Comput 16(2):397–418

    Article  MATH  Google Scholar 

  • Brown PF, Pietra VJD, Pietra SAD, Mercer RL (1993) The mathematics of statistical machine translation: parameter estimation. Comput Linguist 19(2):263–311

    Google Scholar 

  • Chegireddy CR, Hamacher HW (1987) Algorithms for finding K-best perfect matchings. Discrete Appl Math 18(2):155–165

    Article  MathSciNet  MATH  Google Scholar 

  • Chekuri Ch (2010) Min cost perfect matching, CS 598CSC: combinatorial optimization

  • Cho K, Merrienboer BV, Bahdanau D, Bengio Y (2014a) On the properties of neural machine translation: encoder–decoder approaches. In: Proceedings of eighth workshop on syntax, semantics and structure in statistical translation (SSST-8), pp 103–111

  • Cho K, Merrienboer BV, Gulcehre C, Bougares F, Schwenk H, Bengio Y (2014b) Learning phrase representations using RNN encoder–decoder for statistical machine translation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), Doha, Qatar, October, pp 1724–1734

  • Ding Y, Liu Y, Luan H, Sun M (2017) Visualizing and understanding neural machine translation. In: Proceedings of the 55th annual meeting of the Association for Computational Linguistics, pp 1150–1159

  • Gan Zh, Lou D, Zhang Z, Wen X (2015) Bipartite double cover and perfect 2-matching covered graph with its algorithm. Front Math China 10(3):621–634

    Article  MathSciNet  MATH  Google Scholar 

  • Gao W, Wang W, Zheng L (2022) Fuzzy fractional factors in fuzzy graphs. Int J Intell Syst 37(11):9886–9903

    Article  Google Scholar 

  • Goemans MX (2015) Lecture notes on bipartite matching, 18.433: combinatorial optimization. Massachusetts Institute of Technology

  • Gong S, Hua G, Gao W (2021) Domination of bipolar fuzzy graphs in various settings. Int J Comput Intell Syst 14:162. https://doi.org/10.1007/s44196-021-00011-2

    Article  Google Scholar 

  • Hamacher HW, Queyranne M (1983) K-best solutions to combinatorial optimization problems, research report No 83–5 Industrial and Systems Engineering Department, University of Florida. Ann Oper Res 4(1985):123–143

    Google Scholar 

  • Kalchbrenner N, Blunsom P (2013) Recurrent continuous translation models. In: Proceedings of the ACL conference on empirical methods in natural language processing (EMNLP), Seattle, WA, USA, October 18–21, pp 1700–1709

  • Khalili M, Borzooei RA, Deldar M (2021) Matching numbers in fuzzy graphs. J Appl Math Comput. https://doi.org/10.1007/s12190-020-01463-z

    Article  MathSciNet  MATH  Google Scholar 

  • Koehn P, Och FJ, Marcu D (2003) Statistical phrase-based translation. In: Proceedings of the conference of the North American chapter of the Association for Computational Linguistics on Human Language Technology. Stroudsburg, PA, USA 2003, pp 48–54

  • Lawler EL (1972) A procedure for computing the K-th best solutions to discrete optimization problems and its application to the shortest path problem. Manag Sci 18(7):401–405

    Article  MATH  Google Scholar 

  • Li X, Li G, Liu L, Meng M, Shi S (2019) On the word alignment from neural machine translation. In: Proceedings of the 57th annual meeting of the Association for Computational Linguistics, Florence, Italy, August 9, pp 1293–1303

  • Manjusha OT, Sunitha MS (2019) Coverings, matchings and paired domination in fuzzy graphs using strong arcs. Iran J Fuzzy Syst 16(1):145–157

    MathSciNet  MATH  Google Scholar 

  • Mathew S, Mordeson JN, Malik DS (2018) Fuzzy graph theory. Springer, Berlin

    MATH  Google Scholar 

  • Matusov E, Zens R, Ney H (2004) Symmetric word alignments for statistical machine translation. In: Proceedings of the 20th international conference on computational linguistics. https://doi.org/10.3115/1220355.1220387

  • Murty KG (1968) An algorithm for ranking all the assignments in order of increasing cost. Oper Res 16:682–687

    Article  MATH  Google Scholar 

  • Plesnik J (1999) Constrained weighted matchings and edge coverings in graphs. Discrete Appl Math 92:229–241

    Article  MathSciNet  MATH  Google Scholar 

  • Rosenfeld A (1975) Fuzzy graphs. In: Lotfi A. Zadeh, King-Sun Fu, Kokichi Tanaka(eds) Fuzzy sets and their applications to cognitive and decision processes. Academic Press, New York, pp 77–95

  • Roughgarden T (2016) Minimum-cost bipartite matching, CS261: a second course in algorithms

  • Seethalakshmi R, Gnanajothi RB (2014) A note on perfect fuzzy matching. Int J Pure Appl Math 94(2):155–161

    Article  Google Scholar 

  • Sutskever I, Vinyals O, Le Q (2014) Sequence to sequence learning with neural networks. Adv Neural Inf Process Syst 27:3104–3112

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics, Chabahar Branch, Islamic Azad University, Chabahar, Iran

    M. Khalili

  2. Department of Mathematics, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran

    R. A. Borzooei

  3. Department of Mathematics, Faculty of Engineering and Natural Sciences, Istinye University, Istanbul, Turkey

    R. A. Borzooei

  4. Department of Mathematics, Tehran Central Branch, Islamic Azad University, Tehran, Iran

    D. Ebrahimibagha

Authors
  1. M. Khalili
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. R. A. Borzooei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. D. Ebrahimibagha
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to R. A. Borzooei.

Additional information

Communicated by Marcos Eduardo Valle.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Khalili, M., Borzooei, R.A. & Ebrahimibagha, D. A fuzzy model for NMT word alignment using quasi-perfect matching. Comp. Appl. Math. 42, 368 (2023). https://doi.org/10.1007/s40314-023-02498-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s40314-023-02498-1

Keywords

Mathematics Subject Classification

Search

Navigation