• Refine your search:
  • 
    Keyword:
    
    • Slovenian language (12)
    • FOS Computer and information sciences (9)
    • Computation and Language cs.CL (8)
    • BERT (5)
    • language model (5)
    • word embeddings (5)
    • BSc / BA theses (4)
    • MSc / MA theses (4)
    • PhD theses (4)
    • academic writing (4)
    •   more
  • 
    Creator / Publisher:
    
    • Robnik-Šikonja, Marko (47)
    • Ulčar, Matej (13)
    • Arhar Holdt, Špela (10)
    • Krek, Simon (10)
    • Krsnik, Luka (9)
    • Pollak, Senja (9)
    • Žagar, Aleš (9)
    • Dobrovoljc, Kaja (8)
    • Ljubešić, Nikola (8)
    • Erjavec, Tomaž (7)
    •   more
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Page: 1 2 3 Hits 1 – 20 of 52 1 Abstracts from the KAS corpus KAS-Abs 2.0 Žagar, Aleš; Kavaš, Matic; Robnik-Šikonja, Marko. - : Faculty of Electrical Engineering and Computer Science, University of Maribor, 2022. : Faculty of Computer and Information Science, University of Ljubljana, 2022 BASE Show details 2 Corpus of academic Slovene KAS 2.0 Žagar, Aleš; Kavaš, Matic; Robnik-Šikonja, Marko. - : Faculty of Electrical Engineering and Computer Science, University of Maribor, 2022. : Faculty of Computer and Information Science, University of Ljubljana, 2022 BASE Show details 3 Summarization datasets from the KAS corpus KAS-Sum 1.0 Žagar, Aleš; Kavaš, Matic; Robnik-Šikonja, Marko. - : Faculty of Electrical Engineering and Computer Science, University of Maribor, 2022. : Faculty of Computer and Information Science, University of Ljubljana, 2022 BASE Show details 4 Machine Translation datasets from the KAS corpus KAS-MT 1.0 Žagar, Aleš; Kavaš, Matic; Robnik-Šikonja, Marko. - : Faculty of Electrical Engineering and Computer Science, University of Maribor, 2022. : Faculty of Computer and Information Science, University of Ljubljana, 2022 BASE Show details 5 Bayesian BERT for Trustful Hate Speech Detection ... Miok, Kristian; Škrlj, Blaž; Zaharie, Daniela. - : Zenodo, 2022 BASE Show details 6 Bayesian BERT for Trustful Hate Speech Detection ... Miok, Kristian; Škrlj, Blaž; Zaharie, Daniela. - : Zenodo, 2022 BASE Show details 7 Bayesian BERT for Trustful Hate Speech Detection ... Miok, Kristian; Škrlj, Blaž; Zaharie, Daniela. - : Zenodo, 2022 BASE Show details 8 Slovene SuperGLUE Benchmark: Translation and Evaluation ... Žagar, Aleš; Robnik-Šikonja, Marko. - : arXiv, 2022 BASE Show details 9 Valency lexicon extracted from the Gigafida 2.1 corpus Krek, Simon; Gantar, Polona; Krsnik, Luka. - : Centre for Language Resources and Technologies, University of Ljubljana, 2021 BASE Show details 10 Multiword Expressions lexicon extracted from the Gigafida 2.1 corpus Krek, Simon; Gantar, Apolonija; Laskowski, Cyprian. - : Centre for Language Resources and Technologies, University of Ljubljana, 2021 BASE Show details 11 Corpus of Written Standard Slovene Gigafida 2.0 Krek, Simon; Erjavec, Tomaž; Repar, Andraž. - : Centre for Language Resources and Technologies, University of Ljubljana, 2021 BASE Show details 12 List of single-word male and female occupations in Slovenian Supej, Anka; Ulčar, Matej; Robnik-Šikonja, Marko. - : Jožef Stefan Institute, 2021. : Faculty of Computer and Information Science, University of Ljubljana, 2021 BASE Show details 13 SloBERTa: Slovene monolingual large pretrained masked language model ... Ulčar, Matej; Robnik-Šikonja, Marko. - : Zenodo, 2021 BASE Show details 14 Slav-NER: the 3rd Cross-lingual Challenge on Recognition, Normalization, Classification, and Linking of Named Entities across Slavic languages ... Piskorski, Jakub; Babych, Bogdan; Kancheva, Zara. - : Zenodo, 2021 BASE Show details 15 SloBERTa: Slovene monolingual large pretrained masked language model ... Ulčar, Matej; Robnik-Šikonja, Marko. - : Zenodo, 2021 BASE Show details 16 Unsupervised Approach to Cross-Lingual User Comments Summarization ... Žagar, Aleš; Robnik-Šikonja, Marko. - : Zenodo, 2021 BASE Show details 17 Unsupervised Approach to Cross-Lingual User Comments Summarization ... Žagar, Aleš; Robnik-Šikonja, Marko. - : Zenodo, 2021 BASE Show details 18 Slav-NER: the 3rd Cross-lingual Challenge on Recognition, Normalization, Classification, and Linking of Named Entities across Slavic languages ... Piskorski, Jakub; Babych, Bogdan; Kancheva, Zara. - : Zenodo, 2021 BASE Show details 19 Evaluation of contextual embeddings on less-resourced languages ... Ulčar, Matej; Žagar, Aleš; Armendariz, Carlos S.. - : arXiv, 2021 BASE Show details 20 Training dataset and dictionary sizes matter in BERT models: the case of Baltic languages ... Ulčar, Matej; Robnik-Šikonja, Marko. - : arXiv, 2021 Abstract: Large pretrained masked language models have become state-of-the-art solutions for many NLP problems. While studies have shown that monolingual models produce better results than multilingual models, the training datasets must be sufficiently large. We trained a trilingual LitLat BERT-like model for Lithuanian, Latvian, and English, and a monolingual Est-RoBERTa model for Estonian. We evaluate their performance on four downstream tasks: named entity recognition, dependency parsing, part-of-speech tagging, and word analogy. To analyze the importance of focusing on a single language and the importance of a large training set, we compare created models with existing monolingual and multilingual BERT models for Estonian, Latvian, and Lithuanian. The results show that the newly created LitLat BERT and Est-RoBERTa models improve the results of existing models on all tested tasks in most situations. ... : 12 pages. To be published in proceedings of the AIST 2021 conference ... Keyword: Computation and Language cs.CL; FOS Computer and information sciences URL: https://arxiv.org/abs/2112.10553 https://dx.doi.org/10.48550/arxiv.2112.10553 BASE Hide details Page: 1 2 3

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 0 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 1 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 0 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 51 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0