Slovene Language Status Planning
openaire +1 more source
Sustainability-Focused Crypto Protocols Design Methodology for Sensors and IoT with the Deployment of LLMs. [PDF]
Trček D.
europepmc +1 more source
Slovene instruction-following dataset for large language models GaMS-Instruct-MED-Anatomy 1.0
GaMS-Instruct-MED-Anatomy is an instruction-following dataset containing 711,805 prompt-response units in Slovene (with English and Latin terminology).
Žabkar, Ines +7 more
core
Unravelling genetic etiology of cerebral palsy: findings from a Slovenian pediatric cohort. [PDF]
Arkar Silan U +9 more
europepmc +1 more source
Disfluencies in Public and Private Speech. [PDF]
Verdonik D, Rupnik P, Ljubešić N.
europepmc +1 more source
Computer Speech Recognition in Slovene Language
Manual transcription of speech is slow and is being replaced by automatic speech recognition systems. These systems are also used for voice control of various programs and devices. In this thesis, we used as a baseline for Slovene speech recognition GMM-HMM methods for acoustic model and n-grams for language model.
openaire
Synthetic Browsing Histories for 50 Countries Worldwide: Datasets for Research, Development, and Education. [PDF]
Komosny D, Rehman SU, Ayub MS.
europepmc +1 more source
The Influence of Insecure Attachment to Parents on Adolescents' Suicidality. [PDF]
Leben Novak L +5 more
europepmc +1 more source
Statistical analysis of Slovene language corpuses
Natural language processing is an important area of computational linguistics and artificial intelligence . Mostly, its existing applications are developed for and based on English texts. We developed an application for the statistical analysis of large text corpora, which takes into account the unique characteristics of Slovene as a strongly inflected
openaire
Slovene instruction-following dataset for large language models GaMS-Instruct-GEN 1.0
GaMS-Instruct-GEN is an instruction-following dataset designed to fine-tune Slovene large language models to follow instructions. It consists of pairs of prompts and responses, some of which contain an additional input field. The dataset was generated
Ježovnik, Janoš +13 more
core +1 more source

