From 2661d80687b4d00000eea9048cf3bcda370847c8 Mon Sep 17 00:00:00 2001 From: Manuel Romero Date: Tue, 10 Mar 2020 05:10:41 +0100 Subject: [PATCH] Update README.md - Clarify that the model is not trained on the evaluation dataset --- .../mrm8488/bert-multi-cased-finetuned-xquadv1/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/model_cards/mrm8488/bert-multi-cased-finetuned-xquadv1/README.md b/model_cards/mrm8488/bert-multi-cased-finetuned-xquadv1/README.md index 93b734a1cb..82756e8c95 100644 --- a/model_cards/mrm8488/bert-multi-cased-finetuned-xquadv1/README.md +++ b/model_cards/mrm8488/bert-multi-cased-finetuned-xquadv1/README.md @@ -65,7 +65,7 @@ Citation: -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: +As **XQuAD** is just an evaluation dataset, I used `Data augmentation techniques` (scraping, neural machine translation, etc) 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: | Dataset | # samples | | ----------- | --------- |