Intelligent Information Processing

Under the term "intelligent information processing", we summarize algorithmic techniques from the areas of natural language processing, information retrieval, data mining, and artificial intelligence. In our research, we focus on efficient and effective algorithms and systems for tasks like information extraction and text classification, but we also have experience in the area of big data analytics. A detailed description can be found below. 




We use the term "intelligent information processing" to refer to the analysis, understanding, and aggregation of both unstructured data (such as natural language text) and structured data (such as database content). The focus of our research are two of the most important text analysis tasks from natural language processing:

  • Information extraction. We develop algorithms and systems for complex information extraction tasks, such as automatic market forecasting or fine-grained opinion mining. Our goal is to create technologies that qualify for real-world usage in terms of both effectiveness and efficiency.

  • Text classification. We work on new machine learning approaches for existing classification tasks, such as a flow-based sentiment analysis. Also, we introduce new classification tasks, such as the analysis of the language function of a text.

Besides, we have industrial and scientific experience in the development of algorithms for big data analytics, such as ranking functions and clustering techniques.


  • InfexBA – Information Extraction Technology for Business Applications. Development of information extraction technologies for automatic market, trend and sentiment analysis, which was made available in powerful software components for business applications. Funded by the German Federal Ministry of Education and Research. For more information visit the website of the project.
  • ID|SE – Information-Driven Software Engineering. Development of retrieval and extraction algorithms for the recognition of semantic information in software engineering artefacts. Analysis of the possibilities to automatize the software development process using this information.
  • IPRE – Intelligent Personalized Ranking and Recommendation Systems. Development of data mining algorithms for the computation of personalized rankings of the result lists of a hotel booking engine.
  • ArguAna – Argumentation Analysis in Customer Opinion Mining. Development of intelligent technologies for the extraction and classification of opinions from natural language text. Funded by the German Federal Ministry of Education and Research. For more information visit the website of the project.