George Tambouratzis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
George Tambouratzis has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
Marina Vassiliou
Institute of Language & Speech Processing , RC “Athena” Artemidos 6 & Epidavrou str., 15125 Athens , Greece
14 shared publicationsSokratis Sofianopoulos
Institute for Language and Speech Processing
12 shared publicationsGeorge Carayannis
Institute for Language and Speech Processing, Epidavrou & Artemidos 6, 151 25 Maroussi, Greece
4 shared publicationsStella Markantonatou
Institute for Language and Speech Processing
4 shared publicationsNikolaos Hairetakis
Institute for Language and Speech Processing, Epidavrou & Artemidos 6, 151 25 Maroussi, Greece
3 shared publicationsT. J. Stonham
Brunel University
3 shared publications
Latest Publications
- 6 August 2025
- Published by Springer Nature
- p. 225-238
Agentic Correlates of Consciousness and the Pursuit of Artificial General Intelligence
- 6 August 2025
- Published by Springer Nature
- p. 225-238
Agentic Correlates of Consciousness and the Pursuit of Artificial General Intelligence
- Open Access
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 335-341
Evaluating Corpus Cleanup Methods in the WMT’22 News Translation Task
Marilena Malli, George Tambouratzis. Proceedings of the Seventh Conference on Machine Translation (WMT). 2022.
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 335-341
Open AccessEvaluating Corpus Cleanup Methods in the WMT’22 News Translation Task
Marilena Malli, George Tambouratzis. Proceedings of the Seventh Conference on Machine Translation (WMT). 2022.
- 6 October 2021
- Published by Springer Nature
- p. 113-125
Selecting the Optimal Configuration ofSwarm Algorithms for an NLP Task
- 6 October 2021
- Published by Springer Nature
- p. 113-125
Selecting the Optimal Configuration ofSwarm Algorithms for an NLP Task
- Open Access
- 9 May 2019
- Published by Walter de Gruyter GmbH in Journal of Artificial Intelligence and Soft Computing Research
- Vol. 9 (3) , 219-234
Swarm Algorithms for NLP - The Case of Limited Training Data
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 the notion of attraction and repulsion forces between adjacent words. Each of these forces is weighed appropriately by system parameters, the values of which are optimised via particle swarm optimisation. This approach is designed to be language-independent and is tested here for different languages. The phrasing model’s performance is assessed per se, by calculating the segmentation accuracy against a golden segmentation. Operational testing also involves integrating the model to a phrase-based Machine Translation (MT) system and measuring the translation quality when the phrasing model is used to segment input text into phrases. Experiments show that the performance of this approach is comparable to other leading segmentation methods and that it exceeds that of baseline systems.
- 9 May 2019
- Published by Walter de Gruyter GmbH in Journal of Artificial Intelligence and Soft Computing Research
- Vol. 9 (3) , 219-234
Open AccessSwarm Algorithms for NLP - The Case of Limited Training Data
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 the notion of attraction and repulsion forces between adjacent words. Each of these forces is weighed appropriately by system parameters, the values of which are optimised via particle swarm optimisation. This approach is designed to be language-independent and is tested here for different languages. The phrasing model’s performance is assessed per se, by calculating the segmentation accuracy against a golden segmentation. Operational testing also involves integrating the model to a phrase-based Machine Translation (MT) system and measuring the translation quality when the phrasing model is used to segment input text into phrases. Experiments show that the performance of this approach is comparable to other leading segmentation methods and that it exceeds that of baseline systems.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
The effectiveness of surrogate functions in improving the accuracy of PSO-type algorithms in an NLP task
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 relative values of parameters. For this study, a specific Natural Language Processing task is revisited, related to splitting an arbitrary sentence into phrases. In solving this task here, the central idea is to determine if domain-dependent information for expected near-symmetric parameter values can be exploited to reach a better solution in a given number of iterations. If there a known task-specific relation between parameters (for instance the order of magnitude of certain parameters is likely to be similar, as they correspond to similar inputs), the research question is whether such knowledge may be exploited to initially solve a simpler problem in a lower dimensionality. Thus, a hybrid strategy is proposed, that splits the PSO evolution into two phases, (i) the first one optimizing over a reduced set of grouped parameters in order to establish the relative magnitude of each group of related parameters and (ii) the second one optimizing over the entire set of parameters to fine-tune each parameter independently. Two PSO variants are evaluated on this strategy and for each case the results are compared to baselines, to investigate the quality of the solutions achieved. Experimental results indicate that the two variants behave differently with respect to this hybrid strategy, and that one of the PSO variants benefits to generate substantially better optimization solutions.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
The effectiveness of surrogate functions in improving the accuracy of PSO-type algorithms in an NLP task
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 relative values of parameters. For this study, a specific Natural Language Processing task is revisited, related to splitting an arbitrary sentence into phrases. In solving this task here, the central idea is to determine if domain-dependent information for expected near-symmetric parameter values can be exploited to reach a better solution in a given number of iterations. If there a known task-specific relation between parameters (for instance the order of magnitude of certain parameters is likely to be similar, as they correspond to similar inputs), the research question is whether such knowledge may be exploited to initially solve a simpler problem in a lower dimensionality. Thus, a hybrid strategy is proposed, that splits the PSO evolution into two phases, (i) the first one optimizing over a reduced set of grouped parameters in order to establish the relative magnitude of each group of related parameters and (ii) the second one optimizing over the entire set of parameters to fine-tune each parameter independently. Two PSO variants are evaluated on this strategy and for each case the results are compared to baselines, to investigate the quality of the solutions achieved. Experimental results indicate that the two variants behave differently with respect to this hybrid strategy, and that one of the PSO variants benefits to generate substantially better optimization solutions.
- 11 August 2017
- Published by Springer Nature
- p. 1-10
Preliminaries
- 11 August 2017
- Published by Springer Nature
- p. 43-53
Assessing PRESEMT
- 11 August 2017
- Published by Springer Nature
- p. 63-75
Extensions to the PRESEMT Methodology
- 11 August 2017
- Published by Springer Nature
- p. 11-28
Implementation
- 11 August 2017
- Published by Springer Nature
- p. 77-85
Conclusions and Future Work