Research

Publications

  • Romero, J., Razniewski, S., Pal, K., Z. Pan, J., Sakhadeo, A., & Weikum, G. (2019, November). Commonsense properties from query logs and question answering forums. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management (pp. 1411-1420). (pdf)
  • Romero, J., Preda, N., Amarilli, A., & Suchanek, F. (2020, May). Equivalent Rewritings on Path Views with Binding Patterns. In European Semantic Web Conference (pp. 446-462). Springer, Cham. (pdf)
  • Romero, J. (2021, March). Pyformlang: An Educational Library for Formal Language Manipulation. In Proceedings of the 52nd ACM Technical Symposium on Computer Science Education.
  • Romero, J., & Razniewski, S. (2020, October). Inside Quasimodo: Exploring Construction and Usage of Commonsense Knowledge. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management (pp. 3445-3448). (pdf)
  • Romero, J., Preda, N., Amarilli, A., & Suchanek, F. (2020, October). Computing and Illustrating Query Rewritings on Path Views with Binding Patterns. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management (pp. 3449-3452). (pdf)
  • Romero, J., Preda, N., & Suchanek, F. (2020). Query Rewriting On Path Views Without Integrity Constraints. (pdf)

Other Publications

  • Thesis – Harvesting Commonsense and Hidden Knowledge From Web Services (pdf, slides)
  • Master Thesis – Abstractive Text Summarization with Neural Networks (pdf)

Software

Pyformlang

Pyformlang is a Python library to manipulate formal languages. (doc)


Main Projects

Commonsense Knowledge Automatic Harvesting

Commonsense knowledge about object properties, human behavior and general concepts is crucial for robust AI applications. However, automatic acquisition of this knowledge is challenging because of sparseness and bias in online sources. (Learn More)

Discovery of Complex Schemas for RDF Knowledge Bases – Query Rewriting

Web services provide limited access methods to their internal data. In this project, we investigate new methods to combine efficiently these access methods to acquire new information, not originally provided by the data provider. (Learn More)


Further Information