Update README.md
Browse files
README.md
CHANGED
|
@@ -33,16 +33,16 @@ This model aims to simplify German texts into plain German language. It belongs
|
|
| 33 |
- **Developed by:** Regina Stodden
|
| 34 |
- **Model type:** Text2Text Generation
|
| 35 |
- **Language(s) (NLP):** German, Plain German
|
| 36 |
-
|
| 37 |
-
- **Finetuned from model
|
| 38 |
|
| 39 |
-
### Model Sources
|
| 40 |
|
| 41 |
<!-- Provide the basic links for the model. -->
|
| 42 |
|
| 43 |
- **Repository:** [https://huggingface.co/DEplain/mt5-DEplain-APA](https://huggingface.co/DEplain/mt5-DEplain-APA)
|
| 44 |
-
- **Paper
|
| 45 |
-
|
| 46 |
|
| 47 |
## Uses
|
| 48 |
|
|
@@ -137,11 +137,7 @@ The model is fine-tuned on DEplain-APA. DEplain-APA [(Stodden et al., 2023)](htt
|
|
| 137 |
|
| 138 |
We mainly recommend to evaluate mT5-Deplain-APA on [DEplain-APA-sent](DEplain/DEplain-APA-sent). However, in our paper, we include evaluation on more test sets which can be found here: [https://github.com/rstodden/easse-de](https://github.com/rstodden/easse-de/tree/master/easse/resources/data/test_sets/sentence_level).
|
| 139 |
|
| 140 |
-
#### Factors
|
| 141 |
|
| 142 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 143 |
-
|
| 144 |
-
[More Information Needed]
|
| 145 |
|
| 146 |
#### Metrics
|
| 147 |
|
|
@@ -175,7 +171,7 @@ Results of mT5-DEplain-APA and related models evaluated on DEplain-APA. For more
|
|
| 175 |
|
| 176 |
|
| 177 |
|
| 178 |
-
## Citation
|
| 179 |
|
| 180 |
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
|
|
|
|
| 33 |
- **Developed by:** Regina Stodden
|
| 34 |
- **Model type:** Text2Text Generation
|
| 35 |
- **Language(s) (NLP):** German, Plain German
|
| 36 |
+
<!-- **License:** [More Information Needed]-->
|
| 37 |
+
- **Finetuned from model:** [https://huggingface.co/google/mt5-base](https://huggingface.co/google/mt5-base)
|
| 38 |
|
| 39 |
+
### Model Sources
|
| 40 |
|
| 41 |
<!-- Provide the basic links for the model. -->
|
| 42 |
|
| 43 |
- **Repository:** [https://huggingface.co/DEplain/mt5-DEplain-APA](https://huggingface.co/DEplain/mt5-DEplain-APA)
|
| 44 |
+
- **Paper:** Stodden (2024, to appear). "Reproduction & Benchmarking of German Text Simplification Systems" In Proceedings of the 1st Workshop on Evaluating Text Difficulty in a Multilingual Context (DeTermIt!), Turin, Italy.
|
| 45 |
+
<!--- **Demo [optional]:** [More Information Needed]-->
|
| 46 |
|
| 47 |
## Uses
|
| 48 |
|
|
|
|
| 137 |
|
| 138 |
We mainly recommend to evaluate mT5-Deplain-APA on [DEplain-APA-sent](DEplain/DEplain-APA-sent). However, in our paper, we include evaluation on more test sets which can be found here: [https://github.com/rstodden/easse-de](https://github.com/rstodden/easse-de/tree/master/easse/resources/data/test_sets/sentence_level).
|
| 139 |
|
|
|
|
| 140 |
|
|
|
|
|
|
|
|
|
|
| 141 |
|
| 142 |
#### Metrics
|
| 143 |
|
|
|
|
| 171 |
|
| 172 |
|
| 173 |
|
| 174 |
+
## Citation
|
| 175 |
|
| 176 |
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 177 |
|