Update README.md

README.md

@@ -35,19 +35,20 @@ It processes German tax laws as input and outputs the extracted key figures with
 
 ### Model Description
 
-This is a fine-tuned token classification model, based on XLM-RoBERTa-Large, for the extraction of key figures and their logical connected properties from tax legal texts. The entity- and relation extraction tasks are trained in a combined model using initial trigger token to distinguish between the tasks. For relation extraction additional tokens are used to mark the extracted entities and predict the relations between them.
+This is a fine-tuned token classification model, based on XLM-RoBERTa-Large, for the extraction of key figures and their logical connected properties from german tax legal texts. The entity- and relation extraction tasks are trained in a combined model using initial trigger token to distinguish between the tasks. For relation extraction additional tokens are used to mark the extracted entities and predict the relations between them.
 
 
 - **Model type:** fine-tuned token classification model, based on XLM-RoBERTa-Large
 - **Language(s) (NLP):** German
 
-### Model Sources [optional]
+### Model Sources
 
 <!-- Provide the basic links for the model. -->
 
 - **Repository:** https://github.com/danielsteinigen/nlp-legal-texts
 - **Paper:** https://ceur-ws.org/Vol-3441/paper7.pdf
 - **Demo:** https://huggingface.co/spaces/danielsteinigen/NLP-Legal-Texts
+- **Data:** https://huggingface.co/datasets/danielsteinigen/KeyFiTax
 
 ## Uses
 ```python
@@ -87,14 +88,14 @@ Training details can be found in our paper: [https://ceur-ws.org/Vol-3441/paper7
 
 ### Training Data
 
-The model is trained on our dataset __*KeyFiTax*__, which is published here:[https://huggingface.co/datasets/danielsteinigen/KeyFiTax](https://huggingface.co/datasets/danielsteinigen/KeyFiTax)
+The model is trained on our dataset __*KeyFiTax*__, which is published here: [https://huggingface.co/datasets/danielsteinigen/KeyFiTax](https://huggingface.co/datasets/danielsteinigen/KeyFiTax)
 
 ## Evaluation
 
 Evaluation details can be found in our paper: [https://ceur-ws.org/Vol-3441/paper7.pdf](https://ceur-ws.org/Vol-3441/paper7.pdf)
 
 
-## Citation [optional]
+## Citation
 
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 
@@ -115,7 +116,7 @@ Evaluation details can be found in our paper: [https://ceur-ws.org/Vol-3441/pape
 
 **APA:**
 
-Steinigen, D., Namysl, M., Hepperle, M., Krekeler, J., & Landgraf, S. (2023). Semantic Extraction of Key Figures and Their Properties From Tax Legal Texts Using Neural Models.
-Proceedings of Sixth Workshop on Automated Semantic Analysis of Information in Legal Text, Braga, Portugal, June 23, 2023,
+Steinigen, D., Namysl, M., Hepperle, M., Krekeler, J., & Landgraf, S. (2023). Semantic Extraction of Key Figures and Their Properties From Tax Legal Texts Using Neural Models. 
+Proceedings of Sixth Workshop on Automated Semantic Analysis of Information in Legal Text, Braga, Portugal, June 23, 2023. 
 CEUR-WS.org, online CEUR-WS.org/Vol-3441/paper7.pdf.