Blogpost written by Kinga Jelencsik-Mátyus (User Involvement coordinator of HunCLARIN)
Just some days after the annual CLARIN conference in Pisa, on 19 October 2018, the Seminar on Speech and Language Technology Tools took place in Szeged, Hungary.
The general aim of the event was to introduce digital linguistic services to researchers, teachers and students that already working on linguistic projects. The objectives of the workshop was:
to show there are several well-developed, state-of-the-art corpora and software tools available in the fields of historical linguistics, child language and other fields of Humanities and Social Sciences;
to introduce the very basics of using these services;
to show that at HunCLARIN most of these services are available as well as professional help on how to use them.
The seminar will be followed by similar events in other cities (Debrecen is the next) as well as more practical workshops in Szeged.
The organisers (Tamás Erdei, Kinga Jelencsik-Mátyus and Eszter Simon) invited NLP experts of different fields from the Research Institute for Linguistics of the Hungarian Academy of Sciences (Bálint Sass, Iván Mittelholcz, Anna Babarczy and Eszter Simon), as well as from the University of Szeged (Veronika Vincze, Valéria Juhász, Róbert Péter), to present local NLP projects.
There were also posters presented to introduce CLARIN, HunCLARIN and other important projects (connected to Szeged) that make use of or part of the development of HunCLARIN infrastructure.
Over 30 students, teachers and researchers from Szeged, Budapest and other cities in Hungary attended the event. In the first section of the lectures, linguistic corpora, types and possibilities of usage were introduced and practical examples of running simple and more complex searches in corpora were presented. In the second part, two presentations introduced more specific databases: historical and child language corpora. Three presentations were dedicated to software tools:e-magyar (digital language processing toolchain), MAXQDA (a content analysis software) and some tools specially developed for research in Humanities and Social Sciences.
To sum up, the event was an excellent opportunity to introduce the corpora and software tools available at HunCLARIN and to show the projects that make use of the HunCLARIN infrastructure. It was also a great meeting point for students, teachers and researchers of Humanities and Social Sciences who are interested in NLP.
The publication of the online proceedings will soon become available on the event page as well.
For pictures please check the album of the event.
The next event of the HunCLARIN roadshow is already on its way!
See you next time in Debrecen!