Sentence Similarity
sentence-transformers
Safetensors
Serbian
xlm-roberta
wsd
word-sense-disambiguation
serbian
knowledge-distillation
text-embeddings-inference
Instructions to use Tanor/serbian-wsd-distilled-e5-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Tanor/serbian-wsd-distilled-e5-large with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Tanor/serbian-wsd-distilled-e5-large") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Clarify that the dissertation manuscript is unpublished and submitted for evaluation
Browse files- README.md +3 -3
- provenance.json +4 -3
README.md
CHANGED
|
@@ -19,7 +19,7 @@ tags:
|
|
| 19 |
|
| 20 |
This is a Sentence Transformers bi-encoder adapted by **[Saša Petalinkar](https://orcid.org/0009-0007-9664-3594)** from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) for **Serbian word-sense candidate ranking**. Given a sentence context and externally supplied candidate definitions, it ranks the candidates by cosine similarity. Its experiment preset is `mling`.
|
| 21 |
|
| 22 |
-
This
|
| 23 |
|
| 24 |
## Model and intended use
|
| 25 |
|
|
@@ -126,7 +126,7 @@ The checksum identifies the released weight file. Training corpora and external
|
|
| 126 |
|
| 127 |
## Thesis and citation
|
| 128 |
|
| 129 |
-
[Saša Z. Petalinkar](https://orcid.org/0009-0007-9664-3594) (2026). *Machine Learning and Large Language Models in the Development of Semantic Networks and Their Application in Automatic Text Understanding*.
|
| 130 |
|
| 131 |
Original title: *Машинско учење и велики језички модели у развоју семантичких мрежа и њиховој примени на аутоматско разумевање текста*.
|
| 132 |
|
|
@@ -141,7 +141,7 @@ The manuscript does not currently have a public URL or DOI. The [public software
|
|
| 141 |
author = {Petalinkar, Saša Z.},
|
| 142 |
title = {Машинско учење и велики језички модели у развоју семантичких мрежа и њиховој примени на аутоматско разумевање текста},
|
| 143 |
year = {2026},
|
| 144 |
-
note = {
|
| 145 |
language = {Serbian}
|
| 146 |
}
|
| 147 |
```
|
|
|
|
| 19 |
|
| 20 |
This is a Sentence Transformers bi-encoder adapted by **[Saša Petalinkar](https://orcid.org/0009-0007-9664-3594)** from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) for **Serbian word-sense candidate ranking**. Given a sentence context and externally supplied candidate definitions, it ranks the candidates by cosine similarity. Its experiment preset is `mling`.
|
| 21 |
|
| 22 |
+
This model accompanies Saša Z. Petalinkar’s unpublished doctoral dissertation manuscript, submitted for evaluation at the University of Belgrade in 2026. The methodology and reported results are described in Sections 3.4 and 5.8. See [Thesis and citation](#thesis-and-citation) for the full reference.
|
| 23 |
|
| 24 |
## Model and intended use
|
| 25 |
|
|
|
|
| 126 |
|
| 127 |
## Thesis and citation
|
| 128 |
|
| 129 |
+
[Saša Z. Petalinkar](https://orcid.org/0009-0007-9664-3594) (2026). *Machine Learning and Large Language Models in the Development of Semantic Networks and Their Application in Automatic Text Understanding*. Unpublished doctoral dissertation manuscript, submitted for evaluation at the University of Belgrade. Written in Serbian.
|
| 130 |
|
| 131 |
Original title: *Машинско учење и велики језички модели у развоју семантичких мрежа и њиховој примени на аутоматско разумевање текста*.
|
| 132 |
|
|
|
|
| 141 |
author = {Petalinkar, Saša Z.},
|
| 142 |
title = {Машинско учење и велики језички модели у развоју семантичких мрежа и њиховој примени на аутоматско разумевање текста},
|
| 143 |
year = {2026},
|
| 144 |
+
note = {Unpublished doctoral dissertation manuscript, submitted for evaluation at the University of Belgrade. Sections 3.4 and 5.8; Table 5-16},
|
| 145 |
language = {Serbian}
|
| 146 |
}
|
| 147 |
```
|
provenance.json
CHANGED
|
@@ -65,7 +65,7 @@
|
|
| 65 |
"title_english": "Machine Learning and Large Language Models in the Development of Semantic Networks and Their Application in Automatic Text Understanding",
|
| 66 |
"institution": "University of Belgrade",
|
| 67 |
"year": 2026,
|
| 68 |
-
"document_type": "doctoral dissertation manuscript",
|
| 69 |
"language": "Serbian",
|
| 70 |
"method_section": "3.4",
|
| 71 |
"method_section_title": "Разрешење значења речи – дестилација",
|
|
@@ -74,10 +74,11 @@
|
|
| 74 |
"results_table": "5-16",
|
| 75 |
"model_mapping_table": "5-10",
|
| 76 |
"public_url": null,
|
| 77 |
-
"doi": null
|
|
|
|
| 78 |
},
|
| 79 |
"reported_round2_result_source": {
|
| 80 |
-
"type": "doctoral dissertation manuscript and retained experiment summary",
|
| 81 |
"dissertation_section": "5.8",
|
| 82 |
"dissertation_table": "5-16",
|
| 83 |
"evaluation_rerun_for_hub_release": false,
|
|
|
|
| 65 |
"title_english": "Machine Learning and Large Language Models in the Development of Semantic Networks and Their Application in Automatic Text Understanding",
|
| 66 |
"institution": "University of Belgrade",
|
| 67 |
"year": 2026,
|
| 68 |
+
"document_type": "unpublished doctoral dissertation manuscript",
|
| 69 |
"language": "Serbian",
|
| 70 |
"method_section": "3.4",
|
| 71 |
"method_section_title": "Разрешење значења речи – дестилација",
|
|
|
|
| 74 |
"results_table": "5-16",
|
| 75 |
"model_mapping_table": "5-10",
|
| 76 |
"public_url": null,
|
| 77 |
+
"doi": null,
|
| 78 |
+
"status": "submitted for evaluation; not yet defended"
|
| 79 |
},
|
| 80 |
"reported_round2_result_source": {
|
| 81 |
+
"type": "submitted, unpublished doctoral dissertation manuscript and retained experiment summary",
|
| 82 |
"dissertation_section": "5.8",
|
| 83 |
"dissertation_table": "5-16",
|
| 84 |
"evaluation_rerun_for_hub_release": false,
|