Project 13: Relevance Models based on Knowledge Delta

Host Organisation: Research Studios Austria Forschungsgesellschaft mbH, Vienna, Austria

The Research Studios Austria Forschungsgesellschaft mbH operates as an innovative pipeline from Austrian universities to the markets. We are looking for employees who successfully implement, together with our team, research services into the market. The Research Studio Data Science (DSc), located in Vienna, Austria, develops novel methods to make the most value out of company data. The current position offers the possibility of a doctorate degree supervised at TU Wien.

Searching for information is in most cases, particularly in a professional environment, triggered by a lack of knowledge. That means, the user initiates the process in order to find something out rather than to be entertained, for examples. In such professional environments we also, typically, have information about the domain-specific information already available to the user (through business-related communications and documents). Therefore, in this project we want to investigate novel information retrieval models based not solely on the similarity between the linguistic expression of an information need and the content of indexed documents, but also, and primarily, on the difference between the knowledge model of the user and that of the indexed collection. A new formal definition of a user's knowledge, based on the merging of statistical, latent, and explicit semantics is therefore needed.

Main outcome:

  • To define and model of textual similarity as difference in knowledge;
  • To elucidate the relationship between information needs and language representations.

This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 860721