Process Research Group
                                  Bluetooth
Mechatronics,
Signal Processing, Control and Artificial Neural Networks
Department of Information and communications technologies
Technological Centre Ceit /“Researching Today, Creating the Future” 
   
 
   
Natural Language Processing
<< TO BE UPDATED, PLEASE VISIT AGAIN >>
 
Natural Language Processing for Automatic Translation Systems
 
The present project proposes a new approach to measuring efficiency of Natural Language-based Machine Translation. We implement some attributes of evolutionary algorithms performing cosine similarity objective function of a Particle Swarm Optimization (PSO) algorithm then, we evaluate an English text set for translation precision into the Spanish text as a simulated benchmark, and explore the backward process. Our results show that PSO algorithm can be used for translation of multiple language sentences with one identifier only, in other words the technology presented is language-pair independent. Specifically, we indicate that our cosine similarity objective function improves the velocity attribute of the PSO algorithm, making the complex cost functions unnecessary [1].
 
GeneralIdea
 
PSOArchitecture
 
References:
 
[1] Montes Olguín J.A., Mizera-Pietraszko J., Rodriguez Jorge R., Martínez García E.A. (2018) Particle Swarm Optimization as a New Measure of Machine Translation Efficiency. In: Abraham A., Haqiq A., Muda A., Gandhi N. (eds) Proceedings of the Ninth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2017). SoCPaR 2017. Advances in Intelligent Systems and Computing, vol 737. Springer, Cham
 
[2] Jolanta MIZERA-PIETRASZKO, Ricardo RODRIGUEZ JORGE, Grzegorz KOŁACZEK, Edgar Alonso MARTINEZ GARCIA, "Information Streaming Systems: A Review", Intelligent Systems and Applications (INISTA) 2018 Innovations in, pp. 1-9, 2018.
 
[3] Mizera-Pietraszko, Jolanta; Kołaczek, Grzegorz; Rodriguez Jorge, Ricardo, Source-Target Mapping Model of Streaming Data Flow for Machine Translation, INnovations in Intelligent SysTems and Applications (INISTA), 2017 IEEE International Conference on, 3-5 July 2017, Gdynia, Poland. (IEEE Xplore, Web of Science Core Collection Database).