Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,45 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- biogpt
|
| 4 |
+
- boolean-query
|
| 5 |
+
- biomedical
|
| 6 |
+
- systematic-review
|
| 7 |
+
- pubmed
|
| 8 |
+
license: unknown
|
| 9 |
+
model-index:
|
| 10 |
+
- name: BioGPT-BQF-TMK-Large
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
type: text-generation
|
| 14 |
+
name: Text Generation
|
| 15 |
+
dataset:
|
| 16 |
+
name: CLEF TAR
|
| 17 |
+
type: biomedical
|
| 18 |
+
metrics:
|
| 19 |
+
- name: Precision @100
|
| 20 |
+
type: precision
|
| 21 |
+
value: 0.1455
|
| 22 |
+
- name: Recall @1000
|
| 23 |
+
type: recall
|
| 24 |
+
value: 0.2661
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
# BioGPT-BQF-TMK-Large
|
| 28 |
+
Fine-tuned BioGPT for Biomedical Boolean Query Formalization using Titles only.
|
| 29 |
+
|
| 30 |
+
## Model Details
|
| 31 |
+
- Base Model: BioGPT
|
| 32 |
+
- Fine-tuned on: Semi-synthetic generated data
|
| 33 |
+
- Task: Boolean Query Generation for PubMed searches
|
| 34 |
+
|
| 35 |
+
## How to Use
|
| 36 |
+
```python
|
| 37 |
+
from transformers import BioGptForCausalLM, BioGptTokenizer
|
| 38 |
+
|
| 39 |
+
model = BioGptForCausalLM.from_pretrained("AI4BSLR/BioGPT-BQF-TMK-Large")
|
| 40 |
+
tokenizer = BioGptTokenizer.from_pretrained("AI4BSLR/BioGPT-BQF-TMK-Large")
|
| 41 |
+
|
| 42 |
+
input_text = "Title: Heterogeneity in Lung Cancer, MeSH: Biomarkers, Tumor, Genetic Heterogeneity, Keywords: Biomarkers, Query: "
|
| 43 |
+
inputs = tokenizer(input_text, return_tensors="pt")
|
| 44 |
+
outputs = model.generate(**inputs)
|
| 45 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|