Information Extraction and Knowledge Base Population

In this research axis, we are developing semantic models for very different type of data, ranging from multimedia metadata and user social activity on the web to sensor data, in order to support users complex information needs and interaction, such as exploring large information spaces, gathering heterogeneous and distributed information, or personalizing system behaviour. We massively use Linked Data technologies to perform these tasks.

  • Data integration and knowledge base generation aims to develop new techniques for performing large-scale data integration, and in particular, for de-duplicating data objects and for mining knowledge graphs.
  • Natural Language Processing aims to develop new methods for extracting and disambiguating entities from textual documents in order to develop knowledge bases. We also research new methods for extracting sentiments of different type of textual documents (tweets, reviews, etc.)
  • Recommender systems aim to provide novel algorithms and systems that enable to guide users when exploring large information space. We research novel approaches that take into account the semantics of the data as well as usage of the data.

Our research produces concrete software that compete and yield remarkable results in international benchmarks such as SemEval (2017), TAC KBP, the NEEL and OKE challenge.


Syndicate content

Data Science