[PDF][PDF] Language-independent hybrid MT with PRESEMT

G Tambouratzis, S Sofianopoulos… - Proceedings of the …, 2013 - aclanthology.org
The present article provides a comprehensive review of the work carried out on developing
PRESEMT, a hybrid language-independent machine translation (MT) methodology. This …

[PDF][PDF] Improving word translation disambiguation by capturing multiword expressions with dictionaries

L Bungum, B Gambäck, A Lynum… - Proceedings of the 9th …, 2013 - aclanthology.org
The paper describes a method for identifying and translating multiword expressions using a
bi-directional dictionary. While a dictionarybased approach suffers from limited recall …

Conditional Random Fields versus template-matching in MT phrasing tasks involving sparse training data

G Tambouratzis - Pattern Recognition Letters, 2015 - Elsevier
This communication focuses on comparing the template-matching technique to established
probabilistic approaches–such as conditional random fields (CRF)–on a specific linguistic …

[PDF][PDF] Comparing CRF and template-matching in phrasing tasks within a Hybrid MT system

G Tambouratzis - Proceedings of the 3rd Workshop on Hybrid …, 2014 - aclanthology.org
The present article focuses on improving the performance of a hybrid Machine Translation
(MT) system, namely PRESEMT. The PRESEMT methodology is readily portable to new …

Addressing cross-lingual word sense disambiguation on low-density languages: Application to persian

N Rekabsaz, M Lupu, A Hanbury, A Duque - arXiv preprint arXiv …, 2017 - arxiv.org
We explore the use of unsupervised methods in Cross-Lingual Word Sense Disambiguation
(CL-WSD) with the application of English to Persian. Our proposed approach targets the …

Language-independent hybrid MT: Comparative evaluation of translation quality

G Tambouratzis, M Vassiliou… - Hybrid Approaches to …, 2016 - Springer
The present chapter reviews the development of a hybrid Machine Translation (MT)
methodology, which is readily portable to new language pairs. This MT methodology (which …

[PDF][PDF] Expanding the Language model in a low-resource hybrid MT system

G Tambouratzis, S Sofianopoulos… - Proceedings of SSST-8 …, 2014 - aclanthology.org
The present article investigates the fusion of different language models to improve
translation accuracy. A hybrid MT system, recentlydeveloped in the European …

[PDF][PDF] Establishing sentential structure via realignments from small parallel corpora

G Tambouratzis, V Pouli - Proceedings of the Fourth Workshop on …, 2015 - aclanthology.org
The present article reports on efforts to improve the translation accuracy of a corpus–based
hybrid MT system developed using the PRESEMT methodology. This methodology operates …

Word representation for text analysis and search: Document retrieval, sentiment analysis, and cross lingual word sense disambiguation

N Rekabsaz - 2018 - repositum.tuwien.at
Semantics in language is a fundamental aspect of human cognition and in great extent
defines our understanding and knowledge. Word representation methods suggest a …

Assessing PRESEMT

G Tambouratzis, M Vassiliou, S Sofianopoulos… - … Translation with Minimal …, 2017 - Springer
The topic of the current chapter is the evaluation of the performance of PRESEMT both per
se as well as in comparison with other MT systems, the performance relating to the …