Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,27 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
language:
|
4 |
+
- cs
|
5 |
+
tags:
|
6 |
+
- document question answering
|
7 |
---
|
8 |
+
|
9 |
+
# LayoutLMv2 Model Fine-tuned with CIVQA (Tesseract) dataset
|
10 |
+
|
11 |
+
This is a fine-tuned version of the [Impira Document QA model](https://huggingface.co/impira/layoutlm-document-qa), which was trained on Czech Invoice Visual Question Answering (CIVQA) dataset containing invoices in the Czech language as well as on the Data Visualizations via Question Answering ([DVQA] (https://paperswithcode.com/dataset/dvqa)) dataset.
|
12 |
+
|
13 |
+
This model enables Document Visual Question Answering on Czech invoices with the use of the existing DVQA dataset.
|
14 |
+
|
15 |
+
Regarding the Czech invoices, we focused on 10 different entities, which are crucial for processing the invoices.
|
16 |
+
- Variable symbol
|
17 |
+
- Specific symbol
|
18 |
+
- Constant symbol
|
19 |
+
- Bank code
|
20 |
+
- Account number
|
21 |
+
- Total amount
|
22 |
+
- Invoice date
|
23 |
+
- Name of supplier
|
24 |
+
- DIC
|
25 |
+
- QR code
|
26 |
+
|
27 |
+
You can find more information about this model in this [paper](https://nlp.fi.muni.cz/raslan/raslan23.pdf#page=31).
|