13 citations · 15 across the 13 of their papers we have counts for
12 papers · 1 filter
Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments
Ivan Porupski, Nikola Ljubešić
We present three large-scale studies of spoken parliamentary speech across four Slavic languages (Croatian, Czech, Polish, Serbian), drawing on over 6,000 hours from the ParlaSpeec…
Umm... With Transformers? Insights from Filled Pause Use across Four Slavic Parliaments
Ivan Porupski, Branimir Dropuljić, Nikola Ljubešić
Filled pauses (FPs) are a universal feature of spontaneous speech, yet most studies rely on small, single-language corpora, limiting the generalisability of their findings. We anal…
The Growing Gains and Pains of Iterative Web Corpora Crawling: Insights from South Slavic CLASSLA-web 2.0 Corpora
Taja Kuzman Pungeršek, Peter Rupnik, Vít Suchomel +1
Crawling national top-level domains has proven to be highly effective for collecting texts in less-resourced languages. This approach has been recently used for South Slavic langua…
Supercharging Agenda Setting Research: The ParlaCAP Dataset of 28 European Parliaments and a Scalable Multilingual LLM-Based Classification
Taja Kuzman Pungeršek, Peter Rupnik, Daniela Širinić +1
This paper introduces ParlaCAP, a large-scale dataset for analyzing parliamentary agenda setting across Europe, and proposes a cost-effective method for building domain-specific po…
Charting the European LLM Benchmarking Landscape: A New Taxonomy and a Set of Best Practices
Špela Vintar, Taja Kuzman Pungeršek, Mojca Brglez +1
While new benchmarks for large language models (LLMs) are being developed continuously to catch up with the growing capabilities of new models and AI in general, using and evaluati…
State of the Art in Text Classification for South Slavic Languages: Fine-Tuning or Prompting?
Taja Kuzman Pungeršek, Peter Rupnik, Ivan Porupski +2
Until recently, fine-tuned BERT-like models provided state-of-the-art performance on text classification tasks. With the rise of instruction-tuned decoder-only models, commonly kno…
ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian, Czech, Polish, and Serbian
Nikola Ljubešić, Peter Rupnik, Ivan Porupski +1
ParlaSpeech is a collection of spoken parliamentary corpora currently spanning four Slavic languages - Croatian, Czech, Polish and Serbian - all together 6 thousand hours in size.…
CLASSLA-Express: a Train of CLARIN.SI Workshops on Language Resources and Tools with Easily Expanding Route
Nikola Ljubešić, Taja Kuzman, Ivana Filipović Petrović +2
This paper introduces the CLASSLA-Express workshop series as an innovative approach to disseminating linguistic resources and infrastructure provided by the CLASSLA Knowledge Centr…
LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification
Taja Kuzman, Nikola Ljubešić
With the ever-increasing number of news stories available online, classifying them by topic, regardless of the language they are written in, has become crucial for enhancing reader…
Language Models on a Diet: Cost-Efficient Development of Encoders for Closely-Related Languages via Additional Pretraining
Nikola Ljubešić, Vít Suchomel, Peter Rupnik +2
The world of language models is going through turbulent times, better and ever larger models are coming out at an unprecedented speed. However, we argue that, especially for the sc…
CLASSLA-web: Comparable Web Corpora of South Slavic Languages Enriched with Linguistic and Genre Annotation
Nikola Ljubešić, Taja Kuzman
This paper presents a collection of highly comparable web corpora of Slovenian, Croatian, Bosnian, Montenegrin, Serbian, Macedonian, and Bulgarian, covering thereby the whole spect…
Do Language Models Care About Text Quality? Evaluating Web-Crawled Corpora Across 11 Languages
Rik van Noord, Taja Kuzman, Peter Rupnik +4
Large, curated, web-crawled corpora play a vital role in training language models (LMs). They form the lion's share of the training data in virtually all recent LMs, such as the we…