Educational Natural Language Processing

Educational Natural Language Processing (Educational NLP or e-NLP) is aimed at finding new programs of Natural Language Processing for educational reasons, and developing new techniques and software considering the particular needs within the educational domain.

We especially concentrate on NLP programs for eLearning 2.. that is indicated with a worldwide learning community where educational materials are created both by students and instructors. This leads to new challenges for NLP since the quantity of user-produced discourse and social networking content for example wikis and blogs is continually growing as well as intelligent automatic processing.

Language Technologies for eHumanities

The Word What Technologies for eHumanities research group is aimed at research of novel language technology techniques to aid social sciences and humanities research, and scalable and user-friendly web-based services for Digital Humanities.

These technology is designed to offer the imminent paradigm alternation in humanities and social sciences from small, individual studies to responding to (interdisciplinary) research questions based on a sizable empirical basis. The audience can also be thinking about software engineering approaches and finest practices to construct a very modular, sustainable, and open-source natural language processing framework referred to as Darmstadt Understanding Processing Software Repository (DKPro).

Natural Language Processing and Wikis

Natural Language Processing and Wikis (NLP and Wikis) is really a twofold section of research:

  • In Wikis4NLP. we investigate how NLP calculations could be enhanced by using the huge quantity of implicit understanding prevalent in present day wikis instead of using traditional understanding sources like WordNet. Our Application Programming Connects for Wikipedia (JWPL ) and Wiktionary (JWKTL ) permit a competent use of a sizable pool of collaboratively built understanding.
  • In NLP4Wikis. we address the issue that wikis often get disorganized as a consequence of their rapid growth. Using NLP techniques, we attempt to enhance user interaction by supplying suggestions and hints for everyday tasks. The work is completed in the context from the project Wikulu – Self-Organizing Wikis.

Semantic Information Management

Semantic Information Management (SIM) harnesses semantic processing approaches for adding structure to unstructured information for additional accurate, high-precision and-recall information search and retrieval.

Information is available in many forms and formats, including business documents, webpages, user manuals, Frequently asked questions, and software documentation. Within an ever growing mass of knowledge, choosing the best bit of details are becoming a lot more difficult.


These studies area includes two projects: ‘Text mining and knowledge search’ and ‘Extracting and imagining information’. Scientific studies are susceptible to a detailed co-operation using the DIPF graduate programme "Understanding Discovery in Scientific Literature" (KDSL).

The subject of text mining and knowledge search focuses a ideally intuitive, high-quality search way of the net and knowledge sites provided by the data Center for Education. In addition, editors in the German Education Server will be provided with intelligent tools to aid the work they do on producing contents. Whereas the ‘Extracting and imagining information’ concentrates on an automatic extraction of metadata along with other information from unstructured texts which are relevant for search and analysis, in addition to effective visualization and interpretation of these information.