In this work, we examine the ability of NER models to use contextual information when
predicting the type of an ambiguous entity. We introduce NRB, a new testbed carefully …

In this paper we describe a transformer model pre-trained on 8 billion tokens of crawled text
from the Croatian, Bosnian, Serbian and Montenegrin web domains. We evaluate the …

We present experiments on Slovenian, Croatian and Serbian morphosyntactic annotation
and lemmatisation between the former state-of-the-art for these three languages and one of …

Deep learning approaches are superior in natural language processing due to their ability to
extract informative features and patterns from languages. The two most successful neural …

Rezime: Otvorenost jezičkih resursa i alata je od velike važnosti za povećanje kvaliteta i
brzine razvoja tehnologija za računarsku obradu prirodnih jezika. U ovom radu predstavljeni …

Sažetak In this paper, a novel approach to automatic question generation (AQG) using
semantic role labeling (SRL) for morphologically rich languages is presented. A model for …

This paper presents the conversion of the reference language resources for Croatian and
Slovenian morphology processing to UD morphological specifications. We show that the …

This paper analyzes a Named Entity Recognition task for South-Slavic languages using the
pre-trained multilingual neural network models. We investigate whether the performance of …

Networks serve as a metaphor for understanding various phenomena in humanities,
encompassing the circulation of ideas, people, and artifacts. This research employs network …

In this article we present an knowledge extraction approach that can be used in systems that
implement teaching in a fully automated manner. These systems are called Intelligent …