Update README.md

README.md

@@ -60,7 +60,7 @@ pd.DataFrame(output).head()
 
 ## Training and evaluation data
 
-PolicyBERTa-7d was trained on the English-speaking subset of the [Manifesto Project Dataset (MPDS2020a)](https://manifesto-project.wzb.eu/datasets). The model was trained on 115,943 sentences from 163 political manifestos in 7 English-speaking countries (Australia, Canada, Ireland, New Zealand, South Africa, United Kingdom, United States). The manifestos were published between 1992 - 2020. 
+PolicyBERTa-7d was trained on the English-speaking subset of the [Manifesto Project Dataset (MPDS2021a)](https://manifesto-project.wzb.eu/datasets). The model was trained on 115,943 sentences from 163 political manifestos in 7 English-speaking countries (Australia, Canada, Ireland, New Zealand, South Africa, United Kingdom, United States). The manifestos were published between 1992 - 2020. 
 
 | Country        | Count manifestos | Count sentences | Time span        |
 |----------------|------------------|-----------------|--------------------|