Update README.md
Browse files
README.md
CHANGED
|
@@ -20,11 +20,11 @@ tags:
|
|
| 20 |
- PlantStresses
|
| 21 |
- PlantResponses
|
| 22 |
---
|
| 23 |
-
# 🌱
|
| 24 |
|
| 25 |
## Model Description
|
| 26 |
|
| 27 |
-
**
|
| 28 |
This model is part of a broader effort to enable structured knowledge extraction and ontology-aligned information retrieval in **agricultural and biological NLP**.
|
| 29 |
|
| 30 |
The model was trained on a custom-annotated corpus grounded in the **Crop Ontology** and enriched with **part-of-speech (POS) tags and heuristic post-processing**.
|
|
@@ -64,8 +64,8 @@ The model was evaluated on a domain-specific validation set and achieved the fol
|
|
| 64 |
```python
|
| 65 |
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
|
| 66 |
|
| 67 |
-
model = AutoModelForTokenClassification.from_pretrained("PHENOMA/
|
| 68 |
-
tokenizer = AutoTokenizer.from_pretrained("PHENOMA/
|
| 69 |
|
| 70 |
ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer)
|
| 71 |
|
|
@@ -105,7 +105,7 @@ This model supports a custom label set, e.g.:
|
|
| 105 |
|
| 106 |
---
|
| 107 |
## 📚 Dataset
|
| 108 |
-
|
| 109 |
Annotations were performed by plant science experts, ensuring semantic and ontological consistency.
|
| 110 |
|
| 111 |
- **Annotation schema: Aligned with Crop Ontology**
|
|
@@ -129,8 +129,8 @@ This model is released under the MIT License.
|
|
| 129 |
If you use this model in your research or application, please consider citing:
|
| 130 |
|
| 131 |
```bibtex
|
| 132 |
-
@misc{
|
| 133 |
-
title={
|
| 134 |
author={Hiba Khey and Amine Lakhder and Salma Rouichi and Imane El Ghabi and Kamal Hejjaoui and Younes En-nahli and Fahd Kalloubi and Moez Amri},
|
| 135 |
year={2025},
|
| 136 |
eprint={2506.08897},
|
|
|
|
| 20 |
- PlantStresses
|
| 21 |
- PlantResponses
|
| 22 |
---
|
| 23 |
+
# 🌱 PlantDeBERTa: A Domain-Adapted Language Model for Plant Stress and Response NER
|
| 24 |
|
| 25 |
## Model Description
|
| 26 |
|
| 27 |
+
**PlantDeBERTa** is a DeBERTa-based transformer model fine-tuned for **Named Entity Recognition (NER)** in the plant sciences, with a focus on lentil (Lens culinaris) stress-response literature.
|
| 28 |
This model is part of a broader effort to enable structured knowledge extraction and ontology-aligned information retrieval in **agricultural and biological NLP**.
|
| 29 |
|
| 30 |
The model was trained on a custom-annotated corpus grounded in the **Crop Ontology** and enriched with **part-of-speech (POS) tags and heuristic post-processing**.
|
|
|
|
| 64 |
```python
|
| 65 |
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
|
| 66 |
|
| 67 |
+
model = AutoModelForTokenClassification.from_pretrained("PHENOMA/PlantDeBERTa")
|
| 68 |
+
tokenizer = AutoTokenizer.from_pretrained("PHENOMA/PlantDeBERTa")
|
| 69 |
|
| 70 |
ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer)
|
| 71 |
|
|
|
|
| 105 |
|
| 106 |
---
|
| 107 |
## 📚 Dataset
|
| 108 |
+
PlantDeBERTa was trained on a corpus of 142 annotated abstracts related to lentil stress responses, curated from **ScienceDirect**, **SpringerLink**, **Scopus**, etc.
|
| 109 |
Annotations were performed by plant science experts, ensuring semantic and ontological consistency.
|
| 110 |
|
| 111 |
- **Annotation schema: Aligned with Crop Ontology**
|
|
|
|
| 129 |
If you use this model in your research or application, please consider citing:
|
| 130 |
|
| 131 |
```bibtex
|
| 132 |
+
@misc{khey2025plantdebertaopensourcelanguage,
|
| 133 |
+
title={PlantDeBERTa: An Open Source Language Model for Plant Science},
|
| 134 |
author={Hiba Khey and Amine Lakhder and Salma Rouichi and Imane El Ghabi and Kamal Hejjaoui and Younes En-nahli and Fahd Kalloubi and Moez Amri},
|
| 135 |
year={2025},
|
| 136 |
eprint={2506.08897},
|