This is the student project page of an "Application Project" (IN2328).
The ability to structure digital data has become an essential skill of successful organizations. The amount of worldwide available data increases as well as the amount of data in organizations, with significant speed, doubling every two years. This leads to a demand to extract structured information from unstructured data, in particular text data. The goal of this project is to use Natural Language Processing (NLP) to automatically create domain-specific knowledge graphs.
The major research goal of this application project is the application/adaption of existing data science solutions for the automatic creation of domain-specific knowledge graphs from scientific papers of the nanotechnology research domain. The dataset consists of 32+ scientific papers of a German publishing house. A required preparatory work is the identification and preliminary evaluation of suitable algorithms for the information extraction and knowledge graph creation. After that one particular algorithm from one paper or a combination of parts of algorithms from several papers needs to be chosen and adapted to the investigated use case. The quality of the resulting knowledge graph is a key characteristic for the investigated use case. the optimization of the algorithm on is an additional goal of the project.
There are no subpages or files.