Update README.md

README.md

@@ -30,18 +30,18 @@ For training, we used all Maltese data that was present in the [MaCoCu](https://
 
 # Benchmark performance
 
-We tested the performance of MaltBERTa on the UPOS and XPOS benchmark of the [Universal Dependencies](https://universaldependencies.org/) project.  We compare performance to the strong multi-lingual models XLMR-base and XLMR-large, though note that Maltese was not one of the training languages for those models. We also compare to the recently introduced Maltese language models [BERTu](https://huggingface.co/MLRS/BERTu) and [mBERTu](https://huggingface.co/MLRS/mBERTu). For details regarding the fine-tuning procedure you can checkout our [Github](https://github.com/macocu/LanguageModels).
-
-Scores are averages of three runs. We use the same hyperparameter settings for all models.
-
-|                 | **UPOS** | **UPOS** | **XPOS** | **XPOS** |
-|-----------------|:--------:|:--------:|:--------:|:--------:|
-|                 |  **Dev** | **Test** |  **Dev** | **Test** |
-| **XLM-R-base**  |   93.6   |   93.2   |   93.4   |   93.2   |
-| **XLM-R-large** |   94.9   |   94.4   |   95.1   |   94.7   |
-| **BERTu**       |   97.5   |   97.6   |   95.7   |   95.8   |
-| **mBERTu**      |   97.7   |   97.8   |   97.9   |   98.1   |
-| **MaltBERTa**   |   95.7   |   95.8   |   96.1   |   96.0   |
+We tested the performance of MaltBERTa on the UPOS and XPOS benchmark of the [Universal Dependencies](https://universaldependencies.org/) project. Moreover, we test on a Google Translated version of the COPA data set (see our [Github repo](https://github.com/RikVN/COPA) for details). We compare performance to the strong multi-lingual models XLMR-base and XLMR-large, though note that Maltese was not one of the training languages for those models. We also compare to the recently introduced Maltese language models [BERTu](https://huggingface.co/MLRS/BERTu), [mBERTu](https://huggingface.co/MLRS/mBERTu) and our own [MaltBERTa](https://huggingface.co/RVN/MaltBERTa). For details regarding the fine-tuning procedure you can checkout our [Github](https://github.com/macocu/LanguageModels).
+
+Scores are averages of three runs for UPOS/XPOS and 10 runs for COPA. We use the same hyperparameter settings for all models for UPOS/XPOS, while for COPA we optimize on the dev set.
+
+|                 | **UPOS** | **UPOS** | **XPOS** | **XPOS** | **COPA** |
+|-----------------|:--------:|:--------:|:--------:|:--------:| :--------:|
+|                 |  **Dev** | **Test** |  **Dev** | **Test** | **Test** |
+| **XLM-R-base**  |   93.6   |   93.2   |   93.4   |   93.2   |  52.2 |
+| **XLM-R-large** |   94.9   |   94.4   |   95.1   |   94.7   |  54.0 |
+| **BERTu**       |   97.5   |   97.6   |   95.7   |   95.8   |  **55.6** |
+| **mBERTu**      |   **97.7**   |   97.8   |   97.9   |   98.1 |  52.6  |
+| **MaltBERTa**   |   95.7   |   95.8   |   96.1   |   96.0   | 53.7 |
 
 # Acknowledgements