open window

Educational content enriched with links enables learners to look beyond the current text and start learning self-contained in the World Wide Web. Just like looking out of an open window.


open window is concerned to give the opportunity for learners to look into interlinked educational content in the World Wide Web. As part of the Open Window project, technologies for automatic linking educational content with different collaboratively created media are developed. These collaborative created media include encyclopedias, such as Wikipedia, and social media services, such as Twitter.

Automatic linking of educational content is done via the identification of so-called learning elements: learning elements are themes that describe the main concepts of a document. Learning elements are the most important learning concepts present in a document. For example, a document about the American Civil War can have "USA", "Civil War" and "Lincoln" as learning elements. Learning elements are similar to tags, with the restriction that they rely on learning topics. These learning elements can be used to group texts which have the same learning elements and link them together.



The Open Window project is focused on the development of NLP components for processing educational content and its annotations. Educational content can be any kind of document with an educational reference, such as textbooks, lecture notes, forums on education topics and so on.

Challenges to tackle:

  • Identification of individual learning elements (topics);
  • Improvement of annotations, images and opinions descriptions. Some of them might have a poor explanation in a specific context;
  • Link discovery between educational content.

For this purpose, components which must treat faulty texts, as is the case with Twitter or Flickr, have to be developed. Likewise, components for identification of learning elements in educational content and linking these contents have to be developed as well.


We preprocess our data using reusable NLP components from Darmstadt Knowledge Processing Software Repository. Decompounding algorithms, preprocessing components from DKPro Core and keyphrase extractiong methods from DKPro Keyphrases are examples of software components reused by the open window project.


IMC is the industry partner for this Software Campus project. IMC is working in national and international research projects to develop innovations and new products for learning and knowledge management. Thereby the focus lies on the development of new tools and innovative prototypes in the fields of learning management systems, content management, performance support, authoring tools, Web 2.0 applications as well as web-based and mobile platforms.


Project Publications

Additional Attributes


Sense and Similarity: A Study of Sense-level Similarity Measures

Nicolai Erbs, Iryna Gurevych, Torsten Zesch
In: Proceedings of the 3rd Joint Conference on Lexical and Computational Semantics (*SEM 2014), p. 30--39, August 2014
Association for Computational Linguistics and Dublin City University

DKPro Keyphrases: Flexible and Reusable Keyphrase Extraction Experiments

Nicolai Erbs, Pedro Bispo Santos, Iryna Gurevych, Torsten Zesch
In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. System Demonstrations, p. 31-36, June 2014
Association for Computational Linguistics

Hierarchy Identification for Automatically Generating Table-of-Contents

Nicolai Erbs, Iryna Gurevych, Torsten Zesch
In: Proceedings of 9th Conference on Recent Advances in Natural Language Processing (RANLP 2013), p. 252-260, September 2013
A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang