Update README.md
Browse files
README.md
CHANGED
@@ -29,9 +29,6 @@ widget:
|
|
29 |
Fine-tuned model in seven languages on texts from nine countries (Austria, Denmark, Germany, Ireland, Netherlands, Poland, Spain, Sweden, UK), based on [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased). Used in Erfort et al. (2023), building on the PARTYPRESS database. For the downstream task of classyfing press releases from political parties into 23 unique policy areas we achieve a performance comparable to expert human coders.
|
30 |
|
31 |
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
## Model description
|
36 |
|
37 |
The PARTYPRESS multilingual model builds on [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) but has a supervised component. This means, it was fine-tuned using texts labeled by humans. The labels indicate 23 different political issue categories derived from the Comparative Agendas Project (CAP):
|
@@ -151,13 +148,19 @@ When we aggregate the shares of text for each issue, we find that the root-mean-
|
|
151 |
author = {Cornelius Erfort and
|
152 |
Lukas F. Stoetzer and
|
153 |
Heike Klüver},
|
154 |
-
title = {The PARTYPRESS Database: A
|
155 |
journal = {Research and Politics},
|
156 |
-
volume = {
|
|
|
157 |
year = {2023},
|
|
|
|
|
|
|
158 |
}
|
159 |
```
|
160 |
|
|
|
|
|
161 |
### Further resources
|
162 |
|
163 |
Github: [cornelius-erfort/partypress](https://github.com/cornelius-erfort/partypress)
|
|
|
29 |
Fine-tuned model in seven languages on texts from nine countries (Austria, Denmark, Germany, Ireland, Netherlands, Poland, Spain, Sweden, UK), based on [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased). Used in Erfort et al. (2023), building on the PARTYPRESS database. For the downstream task of classyfing press releases from political parties into 23 unique policy areas we achieve a performance comparable to expert human coders.
|
30 |
|
31 |
|
|
|
|
|
|
|
32 |
## Model description
|
33 |
|
34 |
The PARTYPRESS multilingual model builds on [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) but has a supervised component. This means, it was fine-tuned using texts labeled by humans. The labels indicate 23 different political issue categories derived from the Comparative Agendas Project (CAP):
|
|
|
148 |
author = {Cornelius Erfort and
|
149 |
Lukas F. Stoetzer and
|
150 |
Heike Klüver},
|
151 |
+
title = {The PARTYPRESS Database: A new comparative database of parties’ press releases},
|
152 |
journal = {Research and Politics},
|
153 |
+
volume = {10},
|
154 |
+
number = {3},
|
155 |
year = {2023},
|
156 |
+
doi = {10.1177/20531680231183512},
|
157 |
+
URL = {https://doi.org/10.1177/20531680231183512}
|
158 |
+
|
159 |
}
|
160 |
```
|
161 |
|
162 |
+
Erfort, C., Stoetzer, L. F., & Klüver, H. (2023). The PARTYPRESS Database: A new comparative database of parties’ press releases. Research & Politics, 10(3). [https://doi.org/10.1177/20531680231183512](https://doi.org/10.1177/20531680231183512)
|
163 |
+
|
164 |
### Further resources
|
165 |
|
166 |
Github: [cornelius-erfort/partypress](https://github.com/cornelius-erfort/partypress)
|