Feature Extraction
Transformers
PyTorch
Vietnamese
viconbert
bert
wsd
vietnamese
semantic_similarity
custom_code
Instructions to use tkhangg0910/viconbert-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tkhangg0910/viconbert-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="tkhangg0910/viconbert-base", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tkhangg0910/viconbert-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,8 +11,8 @@ tags:
|
|
| 11 |
- vietnamese
|
| 12 |
- semantic_similarity
|
| 13 |
---
|
| 14 |
-
|
| 15 |
# ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations
|
|
|
|
| 16 |
|
| 17 |
This repository is official implementation of the paper: ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations
|
| 18 |
|
|
@@ -102,3 +102,14 @@ sim_2 = cosine_similarity(query_vec_2, query_vec_3)
|
|
| 102 |
print(f"Similarity between 1: {target_1} and 3: {target_3}: {sim_1:.4f}")
|
| 103 |
print(f"Similarity between 2: {target_2} and 3:{target_3}: {sim_2:.4f}")
|
| 104 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
- vietnamese
|
| 12 |
- semantic_similarity
|
| 13 |
---
|
|
|
|
| 14 |
# ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations
|
| 15 |
+
[Model](https://huggingface.co/tkhangg0910/viconbert-base) $~$ [Paper](https://huggingface.co/tkhangg0910/viconbert-base)
|
| 16 |
|
| 17 |
This repository is official implementation of the paper: ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations
|
| 18 |
|
|
|
|
| 102 |
print(f"Similarity between 1: {target_1} and 3: {target_3}: {sim_1:.4f}")
|
| 103 |
print(f"Similarity between 2: {target_2} and 3:{target_3}: {sim_2:.4f}")
|
| 104 |
```
|
| 105 |
+
### Embedding Space Visualization
|
| 106 |
+
|
| 107 |
+
<p align="center">
|
| 108 |
+
<img src="visualization/image_hono.png" width="300"/>
|
| 109 |
+
<img src="visualization/image_poly.png" width="300"/>
|
| 110 |
+
<img src="visualization/image_zeroshot.png" width="300"/>
|
| 111 |
+
</p>
|
| 112 |
+
|
| 113 |
+
<p align="center">
|
| 114 |
+
<em>Contextual separation of "Khoan", "chạy", and zero-shot ability for unseen words</em>
|
| 115 |
+
</p>
|