Spaces:
Runtime error
Runtime error
Commit ·
95ecb1f
1
Parent(s): 545e1c6
Update app.py
Browse files
app.py
CHANGED
|
@@ -90,7 +90,7 @@ demo = gr.Interface(
|
|
| 90 |
|
| 91 |
### About The App
|
| 92 |
|
| 93 |
-
This app is built as a part of the Data Science Weekend 2023 Challenge submission. This app aims to help fertilizer companies to map
|
| 94 |
free-text POS data of multiple types of products into their own fertilizer catalog. By using this app, the company will be able to
|
| 95 |
decide whether a product is already available in their catalog, or whether it is a new product that needs (and eligible) to be added to
|
| 96 |
the catalog. <br>
|
|
@@ -98,15 +98,15 @@ demo = gr.Interface(
|
|
| 98 |
### How Does it Work?
|
| 99 |
|
| 100 |
This app uses a combination of fuzzy matching and machine learning to determine whether a product is already available in the catalog or not.
|
| 101 |
-
When a product is not available in the catalog, we will use
|
| 102 |
added to the catalog. Beforehand, we have fine-tuned the IndoBERT model using a combination of internal and external (web scraping) data, so the
|
| 103 |
model will be able to learn how fertilizer products (especially the local ones) look like. <br>
|
| 104 |
|
| 105 |
-
### What
|
| 106 |
|
| 107 |
-
The flag is a part of the Active Transfer Learning feature of this app. When a user flags
|
| 108 |
will be able to fine-tune the model using the user's input, hence improving the model's performance. So, please help us to improve the model by
|
| 109 |
-
flagging the prediction result
|
| 110 |
|
| 111 |
### I want to test multiple inputs at once!
|
| 112 |
|
|
|
|
| 90 |
|
| 91 |
### About The App
|
| 92 |
|
| 93 |
+
This app is built as a part of the Data Science Weekend (DSW) 2023 Challenge submission. This app aims to help fertilizer companies to map
|
| 94 |
free-text POS data of multiple types of products into their own fertilizer catalog. By using this app, the company will be able to
|
| 95 |
decide whether a product is already available in their catalog, or whether it is a new product that needs (and eligible) to be added to
|
| 96 |
the catalog. <br>
|
|
|
|
| 98 |
### How Does it Work?
|
| 99 |
|
| 100 |
This app uses a combination of fuzzy matching and machine learning to determine whether a product is already available in the catalog or not.
|
| 101 |
+
When a product is not available in the catalog, we will use an IndoBERT model to determine if the product is a fertilizer and eligible to be
|
| 102 |
added to the catalog. Beforehand, we have fine-tuned the IndoBERT model using a combination of internal and external (web scraping) data, so the
|
| 103 |
model will be able to learn how fertilizer products (especially the local ones) look like. <br>
|
| 104 |
|
| 105 |
+
### What are the Flags For?
|
| 106 |
|
| 107 |
+
The flag is a part of the "Active Transfer Learning" feature of this app. When a user flags an output as "Correct" or "Incorrect", the developer
|
| 108 |
will be able to fine-tune the model using the user's input, hence improving the model's performance. So, please help us to improve the model by
|
| 109 |
+
flagging the prediction result 🙏 <br>
|
| 110 |
|
| 111 |
### I want to test multiple inputs at once!
|
| 112 |
|