author={Mikel Artetxe and Sebastian Ruder and Dani Yogatama},
author={Mikel Artetxe and Sebastian Ruder and Dani Yogatama},
title={On the cross-lingual transferability of monolingual representations},
title={On the cross-lingual transferability of monolingual representations},
...
@@ -61,6 +62,7 @@ Citation:
...
@@ -61,6 +62,7 @@ Citation:
eprint={1910.11856}
eprint={1910.11856}
}
}
```
```
</details>
</details>
I used `Data augmentation techniques` and splited the dataset in order to have a train and test set. The test set was created in a way that contains the same number of samples for each language. Finally, I got:
I used `Data augmentation techniques` and splited the dataset in order to have a train and test set. The test set was created in a way that contains the same number of samples for each language. Finally, I got:
author={Mikel Artetxe and Sebastian Ruder and Dani Yogatama},
author={Mikel Artetxe and Sebastian Ruder and Dani Yogatama},
title={On the cross-lingual transferability of monolingual representations},
title={On the cross-lingual transferability of monolingual representations},
...
@@ -59,6 +61,8 @@ Citation:
...
@@ -59,6 +61,8 @@ Citation:
archivePrefix={arXiv},
archivePrefix={arXiv},
eprint={1910.11856}
eprint={1910.11856}
}
}
```
</details>
</details>
I used `Data augmentation techniques` to obtain more samples and splited the dataset in order to have a train and test set. The test set was created in a way that contains the same number of samples for each language. Finally, I got:
I used `Data augmentation techniques` to obtain more samples and splited the dataset in order to have a train and test set. The test set was created in a way that contains the same number of samples for each language. Finally, I got: