Swarm algorithms for NLP-the case of limited training data

G Tambouratzis, M Vassiliou - Journal of Artificial Intelligence and Soft …, 2019 - sciendo.com
The present article describes a novel phrasing model which can be used for segmenting
sentences of unconstrained text into syntactically-defined phrases. This model is based on …

[PDF][PDF] Features of Information System Development of Interactive Communication in Foreign Languages.

T Basyuk, A Vasyliuk, O Vlasenko - COLINS (3), 2024 - ceur-ws.org
The article analyzes existing methods and known systems that provide means of
communication in foreign languages. Technologies and software tools that implement …

Alignment verification to improve NMT translation towards highly inflectional languages with limited resources

G Tambouratzis - Proceedings of the 16th Conference of the …, 2021 - aclanthology.org
The present article discusses how to improve translation quality when using limited training
data to translate towards morphologically rich languages. The starting point is a neural MT …

The effectiveness of surrogate functions in improving the accuracy of PSO-type algorithms in an NLP task

G Tambouratzis - 2017 IEEE Symposium Series on …, 2017 - ieeexplore.ieee.org
The present article investigates a strategy for improving the performance of PSO-type
algorithms when optimizing a set of parameter values, by utilising information regarding the …

Selecting the Optimal Configuration ofSwarm Algorithms for an NLP Task

G Tambouratzis - International Conference on Artificial Intelligence and …, 2021 - Springer
The present article involves the generation of phrase boundaries in unconstrained free text.
Particle Swarm Optimisation (PSO) is applied to determine the optimal values for a set of …

[引用][C] Words divide, pictographs unite: Pictograph communication technologies for people with an intellectual disability

L Sevens - 2018