jonahank commited on
Commit
fca5267
1 Parent(s): 6c5b066

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -9
README.md CHANGED
@@ -1,3 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
  # Identifying and Analysing political quotes from the Danish Parliament related to climate change using NLP
2
  **KlimaBERT**, a sequence-classifier fine-tuned to predict whether political quotes are climate-related. When predicting the class 1, "climate-related", (positive class), the model achieves a F1-score of 0.97, Precision of 0.97, and Recall of 0.97. The negative class, 0, is defined as "non-climate-related".
3
 
@@ -21,12 +33,3 @@ https://www.certainly.io/blog/danish-bert-model/.
21
  ### Acknowledgements
22
  The resources are created through the work of my Master's thesis, so I would like to thank my supervisors [Leon Derczynski](https://www.derczynski.com/itu/) and [Vedran Sekara](https://vedransekara.github.io/) for the great support throughout the project! And a HUGE thanks to [Gustav Gyrst](https://github.com/Gyrst) for great sparring and co-development of the tools you find in this repo.
23
 
24
- ---
25
- language:
26
- - da
27
- - danish
28
-
29
- tags:
30
- - climate change
31
- - climate-classifier
32
- ---
 
1
+ ---
2
+ language:
3
+ - da
4
+ - danish
5
+
6
+ tags:
7
+ - climate change
8
+ - climate-classifier
9
+ - political quotes
10
+
11
+ ---
12
+
13
  # Identifying and Analysing political quotes from the Danish Parliament related to climate change using NLP
14
  **KlimaBERT**, a sequence-classifier fine-tuned to predict whether political quotes are climate-related. When predicting the class 1, "climate-related", (positive class), the model achieves a F1-score of 0.97, Precision of 0.97, and Recall of 0.97. The negative class, 0, is defined as "non-climate-related".
15
 
 
33
  ### Acknowledgements
34
  The resources are created through the work of my Master's thesis, so I would like to thank my supervisors [Leon Derczynski](https://www.derczynski.com/itu/) and [Vedran Sekara](https://vedransekara.github.io/) for the great support throughout the project! And a HUGE thanks to [Gustav Gyrst](https://github.com/Gyrst) for great sparring and co-development of the tools you find in this repo.
35