2026-05-17T04:16:25Zhttp://www.clarin.si/repository/oai/request

oai:www.clarin.si:11356/12572023-05-26T17:30:42Zhdl_11356_1023hdl_11356_1024

ELMo embeddings model, Slovenian Ulčar, Matej ELMo contextual embeddings word embeddings ELMo language model (https://github.com/allenai/bilm-tf) used to produce contextual word embeddings, trained on entire Gigafida 2.0 corpus (https://viri.cjvt.si/gigafida/System/Impressum) for 10 epochs. 1,364,064 most common tokens were provided as vocabulary during the training. The model can also infer OOV words, since the neural network input is on the character level. 2019-10-15 toolService http://hdl.handle.net/11356/1257 slv info:eu-repo/grantAgreement/EC/H2020/825153 http://hdl.handle.net/11356/1277 Apache License 2.0 https://opensource.org/licenses/Apache-2.0 PUB text/plain; charset=utf-8 application/octet-stream application/octet-stream downloadable_files_count: 2 Faculty of Computer and Information Science, University of Ljubljana http://embeddia.eu