Št. zadetkov: 45
Video in druga učna gradiva
Oznake:
humanities;linguistics;lexicography;social sciences;society;computer science
With the rise of digital media in the last decades, many language-related discussions have found
home on various fora and social media such as Facebook, where users can participate in a shared-interest group to discuss language use, problems and resources. The posts in these groups are formulated b ...
Leto:
2018
Vir:
videolectures.net
Video in druga učna gradiva
Oznake:
humanities;linguistics
Avtomatsko luščenje kolokacij temelji predvsem na izračunu statističnih sopojavitev besed v besedilnem korpusu, vsi tako izluščeni kandidati pa niso ustrezni. Da bi opredelili, kaj je legitimna statistična kolokacija na eni in slovarsko relevantna kolokacija na drugi strani, smo pripravili učno množ ...
Leto:
2018
Vir:
videolectures.net
Objavljeni znanstveni prispevek na konferenci
Oznake:
large language models;responsible artificial intelligence;safety datasets;Slovene;
In the paper, we present the initial preparatory phase of the compilation of a Slovene safety dataset containing harmful or offensive prompts and safe responses to them. The dataset will be used to fine-tune Slovene large language models in order to prevent unwanted model behavior and misuse by mali ...
Leto:
2024
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Izvirni znanstveni članek
Oznake:
stalno naglašene enote;naglaševanje;slovenščina;oblikoslovni leksikon;Sloleks;
V prispevku predstavljamo postopek gradnje empirično podprtega izčrpnega seznama naglašenih enot v slovenščini na podlagi Slovenskega oblikoslovnega leksikona Sloleks, in sicer s poudarkom na stalno naglašenih enotah. Obstoječi jezikovni priročniki (npr. Slovenska slovnica, Slovenski pravopis 2001) ...
Leto:
2025
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Objavljeni znanstveni prispevek na konferenci
Oznake:
leksikon;oblikoslovje;pregibanje;širjenje leksikona;hrvaščina;srbščina;lexicon;morphology;inflection;lexicon expansion;Croatian;Serbian;
Open-source machine-readable morphological lexicons are useful for morphosyntactic tagging of corpora and represent a crucial step toward compiling modern digital dictionary databases. In the paper, we present the first step toward extending the functionalities of Pregibalnik, a custom developed ope ...
Leto:
2025
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Objavljeni znanstveni prispevek na konferenci
Oznake:
tabujevsko besedišče;strojno luščenje;vložitve;korpusi;slovenščina;taboo language;automatic extraction;embeddings;Slovene;
We present an approach to extracting candidates to be included in an open-access lexicon of Slovene taboo language by using word embeddings compiled from different Slovene corpora and a set of offensive and pejorative seed lexemes from the Thesaurus of Modern Slovene 2.0. While many studies on taboo ...
Leto:
2025
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Objavljeni znanstveni prispevek na konferenci
Oznake:
multiword expressions;multiword expression variants;statistical analysis;automatic extraction;corpora;
In Slovene linguistics, much research in phraseology has either been theoretical in nature or focused more on compiling lexicographic resources for human users. While several machine-readable lexicographic resources containing multiword expressions (MWEs) have also been developed in recent yea ...
Leto:
2025
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Izvirni znanstveni članek
Oznake:
slovenščina;izgovor črke l;grafemsko-fonemska pretvorba;oblikoslovni leksikon;statistična analiza;
Dvoumnost izgovora črke l v položaju pred soglasniškim grafemom (polža, alge, volilca) predstavlja problem v grafemsko-fonemski pretvorbi za slovenščino in kljub večkratni obravnavi v slovenskih jezikovnih virih še vedno ni razrešena. Zaradi pomanjkanja empiričnih strojno berljivih podatkov o izgovo ...
Leto:
2025
Vir:
Repozitorij Univerze v Ljubljani (RUL)
Video in druga učna gradiva
Oznake:
humanities;linguistics
Leto:
2018
Vir:
videolectures.net
Izvirni znanstveni članek
Oznake:
lemmatization;morphosyntactic tagging;training corpora;morphological lexicon;corpus annotation;
In the paper, we present a new semi-automatic approach to correcting lemmas and morpho-syntactic tags. Unlike previous manual annotation approaches for Slovene corpora, the new method contains an additional step in which tokens and their automatically assigned lemmas and morphosyntactic tags are ...
Leto:
2025
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)