MOLTO's goal is to develop a set of tools for translating texts between multiple languages in real time with high quality. Languages are separate modules in the tool and can be varied; prototypes covering a majority of the EU's 23 official languages will be built.
As its main technique, MOLTO uses domain-specific semantic grammars and ontology-based interlinguas. These componentsare implemented in GF (Grammatical Framework), which is agrammar formalism where multiple languages are related bya common abstract syntax. GF has been applied in severalsmall-to-medium size domains, typically targeting up toten languages but MOLTO will scale this up in terms ofproductivity and applicability.
A part of the scale-up is to increase the size of domainsand the number of languages. A more substantial part is tomake the technology accessible for domain experts without GFexpertise and minimize the effort needed for building atranslator. Ideally, this can be done by just extending alexicon and writing a set of example sentences.
The most research-intensive parts of MOLTO are the two-wayinteroperability between ontology standards (OWL) and GFgrammars, and the extension of rule-based translation bystatistical methods. The OWL-GF interoperability willenable multilingual natural-language-based interaction withmachine-readable knowledge. The statistical methods willadd robustness to the system when desired. New methods willbe developed for combining GF grammars with statisticaltranslation, to the benefit of both.
MOLTO technology will be released as open-source librarieswhich can be plugged in to standard translation tools andweb pages and thereby fit into standard workflows. It willbe demonstrated in web-based demos and applied in threecase studies: mathematical exercises in 15 languages,patent data in at least 3 languages, and museum objectdescriptions in 15 languages.