Commit
•
dd7c21a
1
Parent(s):
6f9626f
adding basic model card (#1)
Browse files- adding basic model card (85cfeab219b92449af1f3dea584a595df91c8938)
Co-authored-by: Ross Kristensen-McLachlan <rdkm89@users.noreply.huggingface.co>
README.md
CHANGED
@@ -1,3 +1,21 @@
|
|
1 |
---
|
2 |
pipeline_tag: summarization
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
pipeline_tag: summarization
|
3 |
+
license: apache-2.0
|
4 |
+
language:
|
5 |
+
- da
|
6 |
+
---
|
7 |
+
|
8 |
+
|
9 |
+
# mT5-small fine-tuned for News article Summarisation ✏️🧾
|
10 |
+
|
11 |
+
[Google's mT5](https://aclanthology.org/2021.naacl-main.41/) for **summarisation** downstream task.
|
12 |
+
|
13 |
+
# Model summary
|
14 |
+
This repository contains a model for Danish abstractive summarisation of news articles. The summariser is based on a language-specific mT5-small.
|
15 |
+
|
16 |
+
The model is fine-tuned using an abstractive subset of the DaNewsroom dataset (Varab & Schluter, 2020), according to the binned density categories employed in Newsroom (Grusky et al., 2019).
|
17 |
+
|
18 |
+
# References
|
19 |
+
Grusky, M., Naaman, M., & Artzi, Y. (2018). Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies. ArXiv:1804.11283 [Cs]. http://arxiv.org/abs/1804.11283
|
20 |
+
|
21 |
+
Varab, D., & Schluter, N. (2020). DaNewsroom: A Large-scale Danish Summarisation Dataset. Proceedings of the 12th Language Resources and Evaluation Conference, 6731–6739. https://aclanthology.org/2020.lrec-1.831
|