edit readme

README.md

@@ -24,15 +24,15 @@ The base model has been finetuned on a Twitter dataset containing text content a
 - **Developed by:** Kateryna Lutsai
 - **Model type:** regression
 - **Language(s) (NLP):** multilingual
-- **Finetuned from model [optional]:** bert-base-multilingual-cased
+- **Finetuned from model:** bert-base-multilingual-cased
 
-### Model Sources [optional]
+### Model Sources
 
 <!-- Provide the basic links for the model. -->
 
 - **Repository:** https://github.com/K4TEL/geo-twitter
-- **Paper [optional]:** https://arxiv.org/submit/4788824/view
-- **Demo [optional]:** https://github.com/K4TEL/geo-twitter/blob/predict/prediction.ipynb
+- **Paper:** https://arxiv.org/pdf/2303.07865.pdf
+- **Demo:** https://github.com/K4TEL/geo-twitter/blob/predict/prediction.ipynb
 
 ## Uses
 
@@ -99,7 +99,7 @@ Information about the model training on the user-defined data could be found in
 ## Evaluation
 
 <!-- This section describes the evaluation protocols and provides the results. -->
-All performance metrics and results are demonstrated in the Results section of the article pre-print: https://arxiv.org/submit/4788824/view
+All performance metrics and results are demonstrated in the Results section of the article pre-print: https://arxiv.org/pdf/2303.07865.pdf
 
 ### Testing Data, Factors & Metrics
 
@@ -119,16 +119,12 @@ Probabilistic metrics: mean and median Cumulative Accuracy Error (CAE), mean and
 ### Results
 
 **Tweet geolocation prediction task**
-
-TEXT-ONLY: mean 1588 km and median 50 km, 61% of Acc@161
-
-NON-GEO: mean 800 km and median 25 km, 80% of Acc@161 
+- TEXT-ONLY: mean 1588 km and median 50 km, 61% of Acc@161
+- NON-GEO: mean 800 km and median 25 km, 80% of Acc@161 
 
 **User home geolocation prediction task**
-
-TEXT-ONLY: mean 892 km and median 31 km, 74% of Acc@161
-
-NON-GEO: mean 567 km and median 26 km, 82% of Acc@161 
+- TEXT-ONLY: mean 892 km and median 31 km, 74% of Acc@161
+- NON-GEO: mean 567 km and median 26 km, 82% of Acc@161 
 
 ### Model Architecture and Objective