Technologies for processing Polish language texts to suit the needs of public security

Project coordinator:

  • Professor Zygmunt Vetulani – Adam Mickiewicz University (AMU).

Sub-project coordinators:

  • Professor Andrzej Dziech (AGH University of Science and Technology, Department of Telecommunications);
  • Professor Wiesław Lubaszewski (AGH University of Science and Technology, Department of Computer Science);
  • Professor Zygmunt Vetulani (Adam Mickiewicz University, Department of Computer Linguistics and Artificial Intelligence).

The institutions performing the project:

  • Adam Mickiewicz University in Poznan (AMU), Faculty of Mathematics and Computer Science, Department of Computer Linguistics and Artificial Intelligence;
  • AGH University of Science and Technology in Crakow (AGH), Faculty of Electrical Engineering, Automatics, Computer Science, and Electronics;
  • Department of Computer Science (DCS) and Department of Telecommunications (DT).

Project objective:

The objective of this project is to develop language and information technologies for processing Polish language texts to be used in applications that will enhance public security.

Project description:

Three pilot applications have been selected to be implemented, the institutions that co-operate in the performance of this project are responsible for these applications. The applications (Topic 1, 2, and 3), require that the existing technology gaps be filled in the area of tools and digital language resources (Topic 4), this is a precondition for successful performance of all other tasks related to language technology application in security and other areas.

  • Topic 1: Communication of a person with an information system in emergency situations, with the use of a natural language (the POLINT-112 system) (AMU);
  • Topic 2: An intelligent court records searching machine developed on the basis of experiences in processing and archiving of copied text (AGH, DT);
  • Topic 3: A system for monitoring Polish language information on the Internet for the purpose of criminal intelligence analysis (AGH, DCS);
  • Topic 4: Construction and expansion of essential electronic information-linguistic tools (AGH, AMU).

The expected measurable results of this project are:

A prototype of a communication support system (emergency-number type) that will process information transferred in a natural language (a text message and, at later stages, voice), with particular focus on crisis management during mass events (such as the Euro 2012) (Topic 1).

A prototype of a court records search machine to look for text and graphics items on the basis of a situational description or key words (Topic 2).

A system for monitoring Polish language information on the Internet for the purpose of criminal analysis (Topic 3).

The generic resources of the Polish language engineering (Topic 4): machine dictionaries, vocabulary registers, ontologies such as WordNet (PolNet) and specialized ontologies, grammars and parsers, text processing algorithms (searching, classification, and “watermarking” algorithms).

 

Project financed by The National Centre for Research and Development

Share on facebook
Share on linkedin
Share on twitter
Share on email
Share on print