2026-04-12T09:44:34Zhttps://clarin.vdu.lt/oai/request

oai:clarin.vdu.lt:20.500.11821/262020-12-24T06:51:43Zhdl_20.500.11821_6hdl_20.500.11821_7

Lithuanian Word embeddings Bielinskienė, Agnė Boizou, Loïc Bumbulienė, Ieva Kovalevskaitė, Jolanta Krilavičius, Tomas Mandravickaitė, Justina Rimkutė, Erika Vilkaitė-Lozdienė, Laura word embeddings Lithuanian embeddings GloVe type word vectors (embeddings) for Lithuanian. Delfi.lt corpus (~70 million words) and StanfordNLP were used for training. The training consisted of several stages: 1) the vocabulary was compiled, eliminating words the the frequency less than 5; 2) word co-occurrence matrix was generated with window size of 5; 3) this matrix was randomly shuffled; 4) word vectors were generated (100 iterations, 200 dimensions). The final result consists of 331 203 unique word vectors. 2019 lexicalConceptualResource http://hdl.handle.net/20.500.11821/26 lit PUB_CLARIN-LT_End-User-Licence-Agreement_EN-LT https://clarin.vdu.lt/licenses/eula/PUB_CLARIN-LT_End-User-Licence-Agreement_EN-LT.htm PUB application/zip text/plain; charset=utf-8 downloadable_files_count: 1 Baltic Institute of Advanced Technology Vytautas Magnus University http://mwe.lt/