Language Technologies cross the boundaries from computational linguistic research on Natural Language Processing to the linguistic research performed at the Institute. This interdisciplinary research is carried out in a two-folded approach:
On the one hand, the language technologies group, together with colleagues from Digital Humanities, is providing, as needed, computational linguistics expertise and technical support to the research efforts of the Multilingualism and Specialised Communication research groups of the Institute. On the other hand, the language technologies group is actively pursuing computational linguistics research, introducing results to running linguistic projects as applicable.
This mutually beneficial approach manifests itself in four correlated research subjects: (Web) Corpora, Visualization of Linguistic Information (LInfoVis), Linguistic Tools and Linguistic Frameworks for Digital Humanities.
Concerning Corpora, the research work aims at enhancing the production and use of monolingual and multilingual text corpora. In addition to corpus design and creation, it includes research on query tools and interfaces. As web corpora are a timely and important topic for the corpus/computational linguistics community, an important focus is put on corpora harvested from the internet.
Research on Linguistic Information Visualization aims at designing graphical representations (visualizations) that enable users to better understand and assess language data by guiding the user's attention and facilitating his navigation and in-depth analysis of large amount of texts. With this objective, visualizations are used to structure data and provide different views that implement several levels of abstraction.
Regarding Linguistic Tools, the research aims at providing tools for the automatic annotation and analysis of textual material. Within this subject, and since the linguistic relevance of most linguistic tools directly or indirectly depends on the quality and coverage of the resources they rely on, a strong focus is set on enhancing the means to develop and and update linguistic resources.
Finally, the everyday cross-border interaction leads to performing research regarding the design of Linguistic Frameworks for Digital Humanities. Within this subject, a focus is put on designing reusable frameworks that abstract away from specific characteristics of single tasks in Digital Humanities so as to make them reusable in contexts with several similar but different objectives.