Mihael Arcan

Identification of Bilingual Terms from Monolingual Documents for Statistical Machine Translation

This publication has emanated from research supported in part by a research grant from Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289 and by the European Union supported projects EuroSentiment (Grant No. 296277), LIDER (Grant No. 610782) and MateCat (ICT-2011.4.2-287688).

Knowledge Portability with Semantic Expansion of Ontology Labels

This publication has emanated from research supported in part by a research grant from Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289 (Insight) and the European Union supported projects LIDER (ICT-2013.4.1-610782) and MixedEmotions (H2020-644632).

Translating Ontologies in Real-World Settings

To enable knowledge access across languages, ontologies that are often represented only in English, need to be translated into different languages. The main challenge in translating ontologies is to disambiguate an ontology label with respect to the domain modelled by ontology itself. Machine translation services may help in this task; however, a crucial requirement is to have translations validated by experts before the ontologies are deployed. For this reason, real-world applications must implement a support system addressing this task to relieve experts in validating all translations. In this paper we present the Expert Supporting System for Ontology Translation, called ESSOT, which exploits the semantic information of the label’s context for improving the quality of label translations. The system has been tested within the Organic.Lingua project by translating the ontology labels in three languages. In order to evaluate further the effectiveness of the system on handling different domains, additional ontologies were translated and evaluated. The results have been compared with translations provided by the Microsoft Translator API and the improvements demonstrate a better performance of the proposed approach for automatic ontology translation.

ESSOT: An Expert Supporting System for Ontology Translation

To enable knowledge access across languages, ontologies, mostly represented only in English, need to be translated into different languages. The main challenge in translating ontologies with machine translation is to disambiguate an ontology label with respect to the domain modelled by the ontology itself; however, a crucial requirement is to have translations validated by experts before the ontologies are deployed. Real-world applications have to implement a support system addressing this task to help experts in validating automatically generated translations. In this paper, we present ESSOT, an Expert Supporting System for Ontology Translation. The peculiarity of this system is to exploit the semantic information of the label’s context to improve the quality of label translations. The system has been tested within the Organic.Lingua project by translating the modelled ontology in three languages, whereby the results are compared with translations provided by the Microsoft Translator API. The provided results demonstrate the viability of our proposed approach.

Leveraging bilingual terminology to improve machine translation in a CAT environment

This work focuses on the extraction and integration of automatically aligned bilingual terminology into a Statistical Machine Translation (SMT) system in a Computer Aided Translation scenario. We evaluate the proposed framework that, taking as input a small set of parallel documents, gathers domain-specific bilingual terms and injects them into an SMT system to enhance translation quality. Therefore, we investigate several strategies to extract and align terminology across languages and to integrate it in an SMT system. We compare two terminology injection methods that can be easily used at run-time without altering the normal activity of an SMT system: XML markup and cache-based model. We test the cache-based model on two different domains (information technology and medical) in English, Italian and German, showing significant improvements ranging from 2.23 to 6.78 BLEU points over a baseline SMT system and from 0.05 to 3.03 compared to the widely-used XML markup approach.