From 758177d22c581ec7a9858217945c276db1a93d6b Mon Sep 17 00:00:00 2001 From: Moritz Laurer Date: Sat, 18 Jun 2022 09:25:01 +0000 Subject: [PATCH] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index c45a9cf..c139fb1 100644 --- a/README.md +++ b/README.md @@ -61,7 +61,7 @@ print(prediction) ``` ### Training data -This model was trained on the XNLI development dataset and the MNLI train dataset. The XNLI development set consists of 5010 professionally translated texts for each of 15 languages (see [this paper](https://arxiv.org/pdf/1809.05053.pdf)). Note that the XNLI contains a training set of 15 machine translated versions of the MNLI dataset for 15 languages, but due to quality issues with these machine translations, this model was only trained on the professional translations from the XNLI development set and the original English MNLI training set (392 702 texts). Not using machine translated texts can avoid overfitting the model to the 15 languages; avoids catastrophic forgetting of the other 85 languages mDeBERTa was pre-trained on; and significantly reduces training costs. +This model was trained on the XNLI development dataset and the MNLI train dataset. The XNLI development set consists of 2490 professionally translated texts for each of 15 languages (37350 in total) (see [this paper](https://arxiv.org/pdf/1809.05053.pdf)). Note that the XNLI contains a training set of 15 machine translated versions of the MNLI dataset for 15 languages, but due to quality issues with these machine translations, this model was only trained on the professional translations from the XNLI development set and the original English MNLI training set (392 702 texts). Not using machine translated texts can avoid overfitting the model to the 15 languages; avoids catastrophic forgetting of the other 85 languages mDeBERTa was pre-trained on; and significantly reduces training costs. ### Training procedure mDeBERTa-v3-base-mnli-xnli was trained using the Hugging Face trainer with the following hyperparameters. @@ -76,7 +76,7 @@ training_args = TrainingArguments( ) ``` ### Eval results -The model was evaluated on the XNLI test set on 15 languages. Note that multilingual NLI models are capable of classifying NLI texts without receiving NLI training data in the specific language (cross-lingual transfer). This means that the model is also able of doing NLI on the other 85 languages mDeBERTa was training on, but performance is most likely lower than for those languages available in XNLI. +The model was evaluated on the XNLI test set on 15 languages (5010 texts per language, 75150 in total). Note that multilingual NLI models are capable of classifying NLI texts without receiving NLI training data in the specific language (cross-lingual transfer). This means that the model is also able of doing NLI on the other 85 languages mDeBERTa was training on, but performance is most likely lower than for those languages available in XNLI. Also note that if other multilingual models on the model hub claim performance of around 90% on languages other than English, the authors have most likely made a mistake during testing since non of the latest papers shows a multilingual average performance of more than a few points above 80% on XNLI (see [here](https://arxiv.org/pdf/2111.09543.pdf) or [here](https://arxiv.org/pdf/1911.02116.pdf)).