KHEYH commited on
Commit
b44b467
·
verified ·
1 Parent(s): 7fdee63

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -20,11 +20,11 @@ tags:
20
  - PlantStresses
21
  - PlantResponses
22
  ---
23
- # 🌱 PlantBert: A Domain-Adapted Language Model for Plant Stress and Response NER
24
 
25
  ## Model Description
26
 
27
- **PlantBert** 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**.
@@ -64,8 +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/PlantBert")
68
- tokenizer = AutoTokenizer.from_pretrained("PHENOMA/PlantBert")
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
- PlantBert 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**
@@ -129,8 +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{khey2025plantbertopensourcelanguage,
133
- title={PlantBert: 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},
 
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},