Migrate model card from transformers-repo
Browse filesRead announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/m3hrdadfi/bert2bert-fa-news-headline/README.md
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: fa
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
tags:
|
| 5 |
+
- summarization
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
A Bert2Bert model on VoA Persian Corpus (a medium-sized corpus of 7.9 million words, 2003-2008) generates headlines. The model achieved a 25.30 ROUGE-2 score.
|
| 9 |
+
|
| 10 |
+
For more detail, please follow the [News Headline Generation](https://github.com/m3hrdadfi/news-headline-generation) repo.
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
## Eval results
|
| 14 |
+
The following table summarizes the ROUGE scores obtained by the Bert2Bert model.
|
| 15 |
+
|
| 16 |
+
| % | Precision | Recall | FMeasure |
|
| 17 |
+
|:-------:|:---------:|:------:|:--------:|
|
| 18 |
+
| ROUGE-1 | 43.78 | 45.52 | 43.54 |
|
| 19 |
+
| ROUGE-2 | 24.50 | 25.30* | 24.24 |
|
| 20 |
+
| ROUGE-L | 41.20 | 42.22 | 40.76 |
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
## Questions?
|
| 24 |
+
Post a Github issue on the [News Headline Generation](https://github.com/hooshvare/news-headline-generation/issues) repo.
|