Learn More
We present a relatively large-scale initiative in high-quality MT based on semantic transfer, reviewing the motivation for this approach, general architecture and components involved, and preliminary experience from a first round of system integration (to be accompanied by a hands-on system demonstration, if appropriate). The translation problem is one(More)
The LOGON project, focusing on machine translation from Norwegian to English, involves three universities (Oslo, Bergen and NTNU Trondheim) and has a public funding from the Norwegian Research Council’s program for language technology (KUNSTI, 2002–2006) on the order of 20 millions NOK. KUNSTI emerged as a reaction to the global growth in language(More)
The present paper reports on an end-to-end application using a deep processing grammar to extract spatial and temporal information of prepositional and adverbial expressions from running text. The extraction process is based on the full understanding of the input text. It is represented in a formalism standard for unification-based grammars and with a(More)
Until recently the accepted view in the linguistic tradition at large has been that lexical verbs uniquely determine the properties of the structures they project in syntax, and that this property of verbs can be captured, modulo framework, as subcategorization frames, argument frames or verb valence. Recent work in the interface of conceptual structure(More)
We suggest a strategy for incremental construction of deep parsing grammars from Interlinear Glossed Text (IGT). IGT is a format of representation where standard linguistics and NLP in principle meet, since they are a data-type which is often available for digitally ‘less resourced languages’ (‘LRL’). The IGT database is TypeCraft (Beermann and Mihaylov(More)