Semantic Similarity: Lubomír Otrusina

Lubomír Otrusina is a researcher at the Brno University of Technology, Faculty of Information Technology

  • 22.3.2017, 12:00 - 13:00

Title: Semantic Similarity (An open lecture)
Speaker: Lubomír Otrusina, Brno University of Technology
When and where: Wednesday the 22nd of March at 12:00 in room V102

Abstract: The human mind has been designed to evaluate the meaning very fast and efficiently. On the other hand, computers are not able to estimate the meaning as precisely as humans. Many models of meaning have been proposed, since semantic similarity plays a very important role in information retrieval and natural language processing area. Generally, the computational models of meaning can be divided into two categories

- knowledge-based models and models based on the distributional hypothesis. The former use manually created resources, such as thesauri, dictionaries or ontologies, to build a meaning model that reflects the real-word state. The latter are based on the distributional hypothesis, which states that similar words tend to occur in similar context. In this talk I will present an overview of the state-of-the art algorithms from both categories.

About the speaker: Lubomír Otrusina is a researcher at the Brno University of Technology, Faculty of Information Technology. He works as a supervisor in Knowledge Technology Research Group (KNOT@FIT) at the faculty. His research is mainly focused on semantic similarity and its application in various natural language processing problems. He participated in several European projects dealing with natural language processing and social networks.