File size: 1,799 Bytes
8758d51 522b4ff 8758d51 5a4f0d1 8758d51 a4570fe 522b4ff 8758d51 522b4ff 3f024bf 77f9e05 5a101d1 8758d51 b23d14a 8758d51 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
---
tags:
- salesken
license: apache-2.0
inference: true
datasets: google_wellformed_query
widget:
text: "she present paper today"
---
This model evaluates the wellformedness (non-fragment, grammatically correct) score of a sentence. Model is case-sensitive and penalises for incorrect case and grammar as well.
['She is presenting a paper tomorrow','she is presenting a paper tomorrow','She present paper today']
[[0.8917],[0.4270],[0.0134]]
1. Dogs are mammals.
2. she loves to read books on history.
3. When the rain in Spain.
4. Eating apples are healthy for you.
5. The Eiffel Tower is in Paris.
Among these sentences:
Sentences 1 and 5 are well-formed and have correct grammar and case.
Sentence 2 starts with a lowercase letter.
Sentence 3 is a fragment and is not well-formed.
Sentence 4 has a subject-verb agreement error.
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("salesken/query_wellformedness_score")
model = AutoModelForSequenceClassification.from_pretrained("salesken/query_wellformedness_score")
sentences = [' what was the reason for everyone to leave the company ',
' What was the reason behind everyone leaving the company ',
' why was everybody leaving the company ',
' what was the reason to everyone leave the company ',
' what be the reason for everyone to leave the company ',
' what was the reasons for everyone to leave the company ',
' what were the reasons for everyone to leave the company ']
features = tokenizer(sentences, padding=True, truncation=True, return_tensors="pt")
model.eval()
with torch.no_grad():
scores = model(**features).logits
print(scores)
```
|