impulse_zimSince December 2012 the German Federal Ministry for Economic Affairs and Energy has funded the project FlexNeuroTrans (Flexible and efficient machine translation for medium-sized businesses using neural nets) of Lingenio in the framework of the ministry’s central innovation programme for medium-sized businesses. Keep on reading.



Hybrid High Quality Translation System (HyghTra) is a joint project of the University of Leeds and Lingenio GmbH which investigates possibilities of rapid construction of hybrid high quality machine translation systems by combining rule based and statistical methods applied to a number of European languages. A main topic of the project is to design declarative core grammars and train them using monolingual and bilingual corpora and translation information. Keep on reading.



Language based Entity Identification for Location Aware Services (LEILAS) proposes to develop applied research on geographical named entities identification and normalization. The project will deliver a technology by which references to geographical entities (towns, addresses…) in web documents will be automatically recognized and assigned spatial coordinates.

The objective of the LEILAS project is the multi-language geo-referenciation for web pages or documents, adding a geographical dimension to text content. Keep on reading.



Rapid Generation of flexible electronic Dictionaries (ReflectDict) is a project funded by the German Federal Ministry of Education and Research (BMBF). In the framework of ReflectDict methods are developed to optimize the construction of dictionaries with respect to (time) costs and quality. Keep on reading (in German).

SFB 732 – Incremental Specification in Context


The special research area (Sonderforschungsbereich – SFB) 732 deals with ambiguity in language, with givenness and representation of underspecified information and with the contextual conditions of gradual specification of such information.

Within SFB 732 cooperation takes place in particular in the subproject B3 Disambiguation of nominalizations in the process of extracting linguistic data from corpora. Lingenio has designed a research tool for the purposes of this project which in particular provides underspecified analyses for the sentences of the considered corpora.