We describe a hybridisation strategy whose objective is to integrate linguistic resources from shallow-transfer rule-based machine translation (RBMT) into phrase-based statistical machine translation (PBSMT). It basically consists of enriching the phrase table of a PBSMT system with bilingual phrase pairs matching transfer rules and dictionary entries from a shallow-transfer RBMT system. This n...

Heloise is a reengineering of the specialised languages for linguistic programming (SLLPs) of Ariane-G5 running both Linux and Windows. Heloise makes the core of Ariane-G5 available to anyone willing to develop “expert” (i.e. relying on linguistic expertise) operational machine translation (MT) systems in that framework, used with success since the 80’s to build many prototypes and a few system...

Ontologies are formal, explicit specifications of shared conceptualizations, representing concepts and their relations that are relevant to a given domain of discourse. Currently, ontologies are mostly developed as well as used through a manual process, which is very ineffective and may cause major barriers to their large-scale use in such areas as Knowledge Discovery and Semantic Web. As human...

We present an approach to the machine translation of French to Arabic in which we explain each of the different steps and some of the problems encountered at each level of linguistic analysis together with their solutions. We show that for high quality translation, an approach which is both global and proper to the couple French to Arabic is necessary, and we compare our approach with existing ...

Moses is a well-known representative of the phrase-based statistical machine translation systems family, which are known to be extremely poor in explicit linguistic knowledge, operating on flat language representations, consisting only of tokens and phrases. Treex, on the other hand, is a highly linguistically motivated NLP toolkit, operating on several layers of language representation, rich i...

This paper describes an improvement in the performance of Transfer-Driven Machine Translation ( T D M T ) by the use of extralinguistic information. In evaluating what constitutes natural speech, particular attention was paid to word usage that depended on the extra-linguistic information from the context, situation, environment and so on. We discuss what types of extra-linguistic information a...

Moses is a well-known representative of the phrase-based statistical machine translation systems family, which are known to be extremely poor in explicit linguistic knowledge, operating on flat language representations, consisting only of tokens and phrases. Treex, on the other hand, is a highly linguistically motivated NLP toolkit, operating on several layers of language representation, rich i...

This paper describes changing needs among the communities that exploit language resources and recent LDC activities and publications that support those needs by providing greater volumes of data and associated resources in a growing inventory of languages with ever more sophisticated annotation. Specifically, it covers the evolving role of data centers with specific emphasis on the LDC, the pub...