behnamsa commited on
Commit
c738df9
1 Parent(s): 6ebd1b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +36 -1
README.md CHANGED
@@ -18,4 +18,39 @@ widget:
18
  example_title: "کتاب"
19
  ---
20
 
21
- # Persian Reverse Dictionary
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  example_title: "کتاب"
19
  ---
20
 
21
+ # Persian Reverse Dictionary
22
+
23
+ This project aims to create a Persian reverse dictionary model that suggests a word based on our input explanations. This model is based on Transformer encoders and uses fast text embedding.
24
+
25
+ ## Dataset
26
+
27
+ The dataset used in this work is from [this link](https://www.kaggle.com/malekzadeharman/persian-reverse-dictionary-dataset). This dataset contains 855,217 data from Amid, Moein, and Dehkhoda dictionaries plus Farsnet and Persian Wikipedia.
28
+
29
+ ## Overall
30
+
31
+ | Metric | Value |
32
+ |--------|-------|
33
+ | Top-10 accuracy | 16.72% |
34
+ | Top-100 accuracy | 33.89% |
35
+ | Top-10 Synonyms accuracy | 42.19% |
36
+ | Top-100 Synonyms accuracy | 62.72% |
37
+
38
+ ## How to use
39
+
40
+ 1. Clone the repository.
41
+ 2. Install the required libraries.
42
+ 3. Import the `PreTrainedPipeline` class from the script.
43
+ 4. Instantiate the pipeline object with the path to the directory where the saved model and other required files are located.
44
+ 5. Call the pipeline object on an input sentence.
45
+
46
+ Here's an example usage:
47
+
48
+ ```python
49
+ from pipeline import PreTrainedPipeline
50
+
51
+ pipeline = PreTrainedPipeline("path/to/directory")
52
+
53
+ result = pipeline("وسیله حمل و نقل پرنده.")
54
+
55
+ print(result)
56
+ ```