Natural Language Processing Centre

The research in Natural Language Processing Centre (NLP Centre) at the Faculty of Informatics, Masaryk University, Brno, is devoted to the following areas:

Large language models, their training and applications with textual and multimodal data (e.g. image, audio and text),
Techniques and methods of machine learning for the purpose of natural language processing such as topic identification, sentiment analysis, style characteristics, or authorship recognition.
Building corpora, tagging and disambiguating corpus text, tools for corpus modification, maintenance, corpus managers and graphical interface for corpora.
Lexical databases with relation to knowledge representation (Czech WordNet and Czech Lexical Database). Tools for viewing and editing dictionaries represented in XML format.
Improvement and further development of the tools for morphological analysis of Czech and other languages, solving the word derivation problems.
Development of syntactic parsers (partial and general) for Czech and other languages and their exploitation as disambiguators.
The problems of syntactic and semantic analysis, knowledge representation and reasoning.
Application of NLP techniques in the area of man-machine communication and internet technologies aiming at analysis, mining and generating of text and speech.

Essential educational goal of the NLP Centre is to offer interesting research opportunities both for pregraduate and postgraduate students and train them within the new field of language engineering.

Take a look at 3D model of the centre.

News

NLP lab members have now automatically access to the NLP Matrix discussion server

We have a new sitting and resting corner in the NLP lab! Please use and enjoy! 🙂

The NLP Centre offers longer term (1-3 years) positions in research and development projects for students of Doctoral programs or Master programs who are planning post gradual studies. These positions are financed via scholarships or as part-time jobs and can significantly increase the standard doctoral scholarship at FI MU. More information: en/PhdCalls

Death announcement about prof.Karel Pala

NLP Centre develops software system supporting the research project Family Names in Britain and Ireland (run by the University of the West of England since 2010). In February 2015, the results of the first phase of the project were submitted to the Oxford University Press, scheduled for publication in 2017.

In 2013, MIT Press published a book by Patrick Hanks with the title Lexical Analysis: Norms and Exploitations. Patrick Hanks worked in NLP Centre at FI MU in the past (2006-2008) under the grant by the Czech Academy of Sciences. In his book, Patrick Hanks offers a wide-ranging empirical investigation of word use and meaning in language. The book fills the need for a lexically based, corpus-driven theoretical approach that will help people understand how words go together in collocational patterns and constructions to make meanings. Lexical Analysis: Norms and Exploitations