Update README.md
Browse files
README.md
CHANGED
@@ -7,4 +7,74 @@ metrics:
|
|
7 |
- rouge
|
8 |
- bertscore
|
9 |
pipeline_tag: summarization
|
10 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
- rouge
|
8 |
- bertscore
|
9 |
pipeline_tag: summarization
|
10 |
+
---
|
11 |
+
# Model Card for Model ID
|
12 |
+
|
13 |
+
### Summarization Model (Type:T5)
|
14 |
+
|
15 |
+
Summarization: Extractive and Abstractive
|
16 |
+
- urT5 adapted from mT5 having monolingual vocabulary only; 40k tokens of Urdu.
|
17 |
+
- Fine-tuned on https://huggingface.co/mbshr/XSUMUrdu-DW_BBC, ref to https://doi.org/10.48550/arXiv.2310.02790 for details.
|
18 |
+
|
19 |
+
|
20 |
+
## Model Details
|
21 |
+
|
22 |
+
### Model Description
|
23 |
+
|
24 |
+
<!-- Provide a longer summary of what this model is. -->
|
25 |
+
|
26 |
+
|
27 |
+
|
28 |
+
- **Developed by:** [More Information Needed]
|
29 |
+
- **Shared by [optional]:** [More Information Needed]
|
30 |
+
- **Model type:** urT5 adapted version of mT5
|
31 |
+
- **Language(s) (NLP):** Urdu
|
32 |
+
- **License:** [More Information Needed]
|
33 |
+
- **Finetuned from model [optional]:** google/mt5-base
|
34 |
+
|
35 |
+
### Model Sources [optional]
|
36 |
+
|
37 |
+
<!-- Provide the basic links for the model. -->
|
38 |
+
|
39 |
+
- **Repository:** [More Information Needed]
|
40 |
+
- **Paper [optional]:** https://doi.org/10.48550/arXiv.2310.02790
|
41 |
+
|
42 |
+
## Uses
|
43 |
+
|
44 |
+
Summarization
|
45 |
+
|
46 |
+
## How to Get Started with the Model
|
47 |
+
|
48 |
+
Use the code below to get started with the model.
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
## Training Details
|
53 |
+
|
54 |
+
|
55 |
+
## Evaluation & Results
|
56 |
+
|
57 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
58 |
+
|
59 |
+
Evaluated on https://huggingface.co/mbshr/XSUMUrdu-DW_BBC
|
60 |
+
- ROUGE-1 F Score: 40.03 combined, 46.35 BBC Urdu datapoints only and 36.91 DW Urdu datapoints only)
|
61 |
+
- BERTScore: 75.1 combined, 77.0 BBC Urdu datapoints only and 74.16 DW Urdu datapoints only
|
62 |
+
|
63 |
+
## Citation [optional]
|
64 |
+
|
65 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
66 |
+
|
67 |
+
@misc{munaf2023low,
|
68 |
+
title={Low Resource Summarization using Pre-trained Language Models},
|
69 |
+
author={Mubashir Munaf and Hammad Afzal and Naima Iltaf and Khawir Mahmood},
|
70 |
+
year={2023},
|
71 |
+
eprint={2310.02790},
|
72 |
+
archivePrefix={arXiv},
|
73 |
+
primaryClass={cs.CL}
|
74 |
+
}
|
75 |
+
|
76 |
+
## Contact
|
77 |
+
|
78 |
+
- mubashir.munaaf@gmail.com
|
79 |
+
|
80 |
+
|