Regional Linguistic Data Initiative (ReLDI)

Tanja Samardžić, Nikola Ljubešić, Maja Miličević
This year we received 29 submissions, out of which 16 were accepted for presentation: 13 as regular papers and three as interactive presentations (resulting in an overall acceptance rate of 55%). Compared to previous BSNLP workshops, this year we have a mixed balance of papers on enabling technologies and higher-level tasks, such as information extraction, sentiment analysis and text classification. This shows the ongoing trend towards building user-oriented applications for Balto-Slavic
more » ... es, in addition to working on lower-level NLP tools. The papers directly deal with at least seven Balto-Slavic languages: Bulgarian, Croatian, Czech, Lithuanian, Polish, Russian, and Serbian. Three of the papers discuss approaches to syntactic and semantic analysis. Three papers are about information extraction. Three papers cover sentiment analysis and text classification. Other papers address a broad range of topics, including word-sense disambiguation, corpus analysis, text and author modeling, and linguistic resources. It is our sincere hope that this work will help to further strengthen the community and stimulate the growth of research in this rich and exciting field.
doi:10.5167/uzh-127250 fatcat:tuiafgzehzhtfhtf53sz3wafqa