Workshop 1
The FrameNet Brasil Framework

Workshop 2
CLASSLA-Express 3.0

Workshop 3
TESLA: language resources

Workshop 4
TESLA: From Text to Knowledge Graphs

TESLA: language resources

Use of language resources developed within the framework of the TESLA project with a focus on the TESLA portal.

Workshop Description

A number of language resources and tools for text processing in Serbian were developed within the TESLA project, with the aim of supporting practical application in a digital environment. This workshop aims to provide participants with a comprehensive insight into the capabilities of some of the tools, as well as to show how they can be used through an open portal intended for the wider community.

Special emphasis is placed on modern text processing, which includes normalization, transliteration, annotation, vector analysis and the application of language models. Participants will have the opportunity to familiarize themselves with how these tools enable this process.

The workshop is designed to offer participants a combination of theoretical introduction and practical work, allowing them to acquire concrete knowledge and skills through interactive examples. In this way, participants will not only understand how the tools work, but will also be able to apply them themselves.

Practical Session

Participants will test individual portal functionalities such as text normalization and transliteration, annotation, vector analysis, and the use of language models for text processing.

They will:

• transliterate text from Cyrillic to Latin and vice versa with a focus on special examples and exceptions;
• annotate text in the form of part-of-speech tagging and lemmatization;
• calculate word similarity in Serbian using various algorithms for static vectorization;
• convert text to vector and perform vector operations;
• vectorize text in separate vector spaces (emotion and evocation of emotions);
• visualize and analyze the obtained results.

Who is the workshop for?

The workshop is intended for everyone who is interested in language resources and text processing in the Serbian language.

Organizers:

• Dr Mihailo Škorić, University of Belgrade – Faculty of Mining and Geology
• Dr Biljana Rujević, University of Belgrade – Faculty of Mining and Geology
• Dr Milica Dinić Marinković, University of Belgrade – Faculty of Philology
• Dr Ranka Stanković, University of Belgrade – Faculty of Mining and Geology
• Saša Petalinkar, University of Belgrade – Faculty of Mining and Geology