Abstract
With the increase of translation demand, the advancement of information technology, the development of linguistic theories and the progress of natural language understanding models in artificial intelligence research, machine translation has gradually gained worldwide attention. However, at present, machine translation research still has problems such as insufficient bilingual data and lack of effective feature representation, which affects the further improvement of key modules of machine translation such as word alignment, sequence adjustment and translation modelling. The effect of machine translation is still unsatisfactory. As a new machine learning method, deep neural network can automatically learn abstract feature representation and establish a complex mapping relationship between input and output signals, which provides a new idea for statistical machine translation research. Firstly, the multi-layer neural network and the undirected probability graph model are combined, and the similarity and context information of vocabulary are effectively utilized to model the word alignment more fully, and the word alignment model named NNWAM is constructed. Secondly, the low dimension will be used. The feature representation is combined with other features into a linearly ordered pre-ordering model to construct the pre-ordering model named NNPR. Finally, the word alignment model and the pre-ordering model are combined in the same deep neural network framework to form DNNAPM, a statistical machine translation model based on deep neural networks. The experimental results show that the statistical machine translation model based on deep neural network has better effect, faster convergence and better reliability than the comparison model algorithm.
Similar content being viewed by others
References
Claycomb J, Abreu-Goodger C, Buck AH (2017) RNA-mediated communication between helminths and their hosts: the missing links. RNA Biol 14(4):436–441
Su J, Zeng J, Xiong D et al (2018) A hierarchy-to-sequence attentional neural machine translation model. IEEE/ACM Trans Audio Speech Lang Process 26(3):623–632
Lo B, Zettler P, Cedars MI et al (2010) A new era in the ethics of human embryonic stem cell research. Stem Cells 23(10):1454–1459
Curtmola R, Garay J, Kamara S et al (2011) Searchable symmetric encryption: improved definitions and efficient constructions. J Comput Secur 19(5):895–934
Sun Y, Xu J, Qiang H et al (2019) Adaptive sliding mode control of maglev system based on RBF neural network minimum parameter learning method. Measurement 141:217–226
Chakraborty S, Khasidashvili Z, Seger CJH et al (2017) Symbolic trajectory evaluation for word-level verification: theory and implementation. Form Methods Syst Des 50(2–3):1–36
Kim K, Park EJ, Shin JH et al (2017) Divergence-based fine pruning of phrase-based statistical translation model. Comput Speech Lang 41(C):146–160
Dai X-G, Wang P (2017) A new classification of large-scale climate regimes around the Tibetan Plateau based on seasonal circulation patterns. Adv Clim Change Res 8(1):26–36
Ashraf N, Ahmad M (2015) Machine translation techniques and their comparative study. Int J Comput Appl 125(7):25–31
Gao S, Yang X, Yu Z et al (2017) Chinese-Naxi machine translation method based on Naxi dependency language model. Int J Mach Learn Cybern 8(1):333–342
Dong W, Chi M (2017) Long short-term memory with quadratic connections in recursive neural networks for representing compositional semantics. IEEE Access 5:16077–16083
Zhang X, Liang Y, Chen L et al (2017) Recursive autoencoders-based unsupervised feature learning for hyperspectral image classification. IEEE Geosci Remote Sens Lett 14(11):1928–1932
Wang S, Cong Y, Cao J et al (2016) Scalable gastroscopic video summarization via similar-inhibition dictionary selection. Artif Intell Med 66:1–13
Guzmán F, Joty S, Màrquez L et al (2017) Machine translation evaluation with neural networks. Comput Speech Lang 45:180–200
Ding C, Sakanushi K, Touji H et al (2016) Inter-, intra-, and extra-chunk pre-ordering for statistical Japanese-to-English machine translation. ACM Trans Asian Low Resour Lang Inf Process 15(3):1–28
Chong CC, Lim TY, Soon LK et al (2017) Meaning preservation in example-based machine translation with structural semantics. Expert Syst Appl 78:242–258
Hasler E, Gispert AD, Stahlberg F et al (2017) Source sentence simplification for statistical machine translation. Comput Speech Lang 45(C):221–235
Song Z (2017) The research on key technologies of chinese heavy-lift launch vehicle control system. Aerosp China 18(2):13–22
Marmanis D, Datcu M, Esch T et al (2016) Deep learning earth observation classification using imagenet pretrained networks. IEEE Geosci Remote Sens Lett 13(1):105–109
Weber M, Fackeldey K, Schütte C (2017) Set-free Markov state model building. J Chem Phys 146(12):124133
Shen M, Dan Y (2017) A finite frequency approach to control of Markov jump linear systems with incomplete transition probabilities. Appl Math Comput 295:53–64
Kang L, Xu L, Zhao J (2018) Co-extracting opinion targets and opinion words from online reviews based on the word alignment model. IEEE Trans Knowl Data Eng 27(3):636–650
Wu ZG, Ju HP, Su H et al (2012) Passivity analysis of Markov jump neural networks with mixed time-delays and piecewise-constant transition rates. Nonlinear Anal Real World Appl 13(5):2423–2431
Mo YY, Guo JY, Yu ZT et al (2015) A bilingual word alignment algorithm of Vietnamese–Chinese based on feature constraint. Int J Mach Learn Cybern 6(4):537–543
Liu Y (2019) Digital image recognition based on improved cognitive neural network. Transl Neurosci 10(1):125–128
He W (2019) Computational neuroscience applied in surface roughness fiber optic sensor. Transl Neurosci 10(1):70–75
Chen MC, Lu SQ, Liu QL (2018) Global regularity for a 2D model of electro-kinetic fluid in a bounded domain. Acta Mathematicae Applicatae Sinica, Engl Ser 34(2):398–403
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xia, Y. Research on statistical machine translation model based on deep neural network. Computing 102, 643–661 (2020). https://doi.org/10.1007/s00607-019-00752-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00607-019-00752-1