Views
No views yet
GloVe Sr | |
|
Обучаван над корпусом српског језика - 9.5 милијарди речи
|
Trained on the Serbian language corpus - 9.5 billion words
|
1from gensim.models import KeyedVectors
2from huggingface_hub import snapshot_download
3
4local_dir = snapshot_download(repo_id="te-sla/GloVeSr",
5allow_patterns=["*.kv", "*npy"])
6vectors = KeyedVectors.load(local_dir + "/glove_keyed_vectors.kv")
7print(vectors.most_similar("klijent", topn=5))[('prethodnik', 0.8428025245666504),
('saputnik', 0.8391610383987427),
('suprug', 0.8257851004600525),
('premijerov', 0.8162577748298645),
('maleni', 0.8144716620445251)]1@inproceedings{stankovic-dict2vec,
2 author = {Ranka Stanković, Jovana Rađenović, Mihailo Škorić, Marko Putniković},
3 title = {Learning Word Embeddings using Lexical Resources and Corpora},
4 booktitle = {15th International Conference on Information Society and Technology, ISIST 2025, Kopaonik},
5 year = {2025},
6 address = {Kopaonik, Belgrade}
7 publisher = {SASA, Belgrade},
8 url = {https://doi.org/10.5281/zenodo.15093900}
9}
|
Истраживање jе спроведено уз подршку Фонда за науку Републике Србиjе, #7276, Text Embeddings – Serbian Language Applications – TESLA
|
This research was supported by the Science Fund of the Republic of Serbia, #7276, Text Embeddings - Serbian Language Applications - TESLA
|