From 1121ce9f98f718d67c3976dd30bb44933730ad56 Mon Sep 17 00:00:00 2001 From: Sai Saketh Aluru Date: Wed, 24 Jun 2020 21:11:08 +0530 Subject: [PATCH] Model cards for Hate-speech-CNERG models (#5236) * Add dehatebert-mono-arabic readme card * Update dehatebert-mono-arabic model card * model cards for Hate-speech-CNERG models --- model_cards/Hate-speech-CNERG/dehatebert-mono-arabic/README.md | 2 +- model_cards/Hate-speech-CNERG/dehatebert-mono-english/README.md | 2 +- model_cards/Hate-speech-CNERG/dehatebert-mono-french/README.md | 2 ++ model_cards/Hate-speech-CNERG/dehatebert-mono-german/README.md | 2 ++ .../Hate-speech-CNERG/dehatebert-mono-indonesian/README.md | 2 ++ model_cards/Hate-speech-CNERG/dehatebert-mono-italian/README.md | 2 ++ model_cards/Hate-speech-CNERG/dehatebert-mono-polish/README.md | 2 ++ .../Hate-speech-CNERG/dehatebert-mono-portugese/README.md | 2 ++ model_cards/Hate-speech-CNERG/dehatebert-mono-spanish/README.md | 2 ++ 9 files changed, 16 insertions(+), 2 deletions(-) create mode 100644 model_cards/Hate-speech-CNERG/dehatebert-mono-french/README.md create mode 100644 model_cards/Hate-speech-CNERG/dehatebert-mono-german/README.md create mode 100644 model_cards/Hate-speech-CNERG/dehatebert-mono-indonesian/README.md create mode 100644 model_cards/Hate-speech-CNERG/dehatebert-mono-italian/README.md create mode 100644 model_cards/Hate-speech-CNERG/dehatebert-mono-polish/README.md create mode 100644 model_cards/Hate-speech-CNERG/dehatebert-mono-portugese/README.md create mode 100644 model_cards/Hate-speech-CNERG/dehatebert-mono-spanish/README.md diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-arabic/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-arabic/README.md index ac36da2e72..e90a6e80e9 100644 --- a/model_cards/Hate-speech-CNERG/dehatebert-mono-arabic/README.md +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-arabic/README.md @@ -1,2 +1,2 @@ This model is used detecting **hatespeech** in **Arabic language**. The mono in the name refers to the monolingual setting, where the model is trained using only Arabic language data. It is finetuned on multilingual bert model. -The model is trained with different learning rates and the best validation score achieved is 0.8674776 for a learning rate of 2e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) +The model is trained with different learning rates and the best validation score achieved is 0.877609 for a learning rate of 2e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-english/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-english/README.md index b96c834b86..76b8ed7c2e 100644 --- a/model_cards/Hate-speech-CNERG/dehatebert-mono-english/README.md +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-english/README.md @@ -1,2 +1,2 @@ This model is used detecting **hatespeech** in **English language**. The mono in the name refers to the monolingual setting, where the model is trained using only English language data. It is finetuned on multilingual bert model. -The model is trained with different learning rates and the best validation score achieved is 0.7069374 for a learning rate of 2e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) +The model is trained with different learning rates and the best validation score achieved is 0.726030 for a learning rate of 2e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-french/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-french/README.md new file mode 100644 index 0000000000..914426d5f9 --- /dev/null +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-french/README.md @@ -0,0 +1,2 @@ +This model is used detecting **hatespeech** in **French language**. The mono in the name refers to the monolingual setting, where the model is trained using only English language data. It is finetuned on multilingual bert model. +The model is trained with different learning rates and the best validation score achieved is 0.692094 for a learning rate of 3e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-german/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-german/README.md new file mode 100644 index 0000000000..4b7b29d3b6 --- /dev/null +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-german/README.md @@ -0,0 +1,2 @@ +This model is used detecting **hatespeech** in **German language**. The mono in the name refers to the monolingual setting, where the model is trained using only English language data. It is finetuned on multilingual bert model. +The model is trained with different learning rates and the best validation score achieved is 0.649794 for a learning rate of 3e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-indonesian/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-indonesian/README.md new file mode 100644 index 0000000000..92cb0da1ef --- /dev/null +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-indonesian/README.md @@ -0,0 +1,2 @@ +This model is used detecting **hatespeech** in **Indonesian language**. The mono in the name refers to the monolingual setting, where the model is trained using only Arabic language data. It is finetuned on multilingual bert model. +The model is trained with different learning rates and the best validation score achieved is 0.844494 for a learning rate of 2e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-italian/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-italian/README.md new file mode 100644 index 0000000000..6112e38225 --- /dev/null +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-italian/README.md @@ -0,0 +1,2 @@ +This model is used detecting **hatespeech** in **Italian language**. The mono in the name refers to the monolingual setting, where the model is trained using only English language data. It is finetuned on multilingual bert model. +The model is trained with different learning rates and the best validation score achieved is 0.837288 for a learning rate of 3e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-polish/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-polish/README.md new file mode 100644 index 0000000000..51edc8d5b0 --- /dev/null +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-polish/README.md @@ -0,0 +1,2 @@ +This model is used detecting **hatespeech** in **Polish language**. The mono in the name refers to the monolingual setting, where the model is trained using only English language data. It is finetuned on multilingual bert model. +The model is trained with different learning rates and the best validation score achieved is 0.723254 for a learning rate of 2e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-portugese/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-portugese/README.md new file mode 100644 index 0000000000..f8436685b1 --- /dev/null +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-portugese/README.md @@ -0,0 +1,2 @@ +This model is used detecting **hatespeech** in **Portuguese language**. The mono in the name refers to the monolingual setting, where the model is trained using only English language data. It is finetuned on multilingual bert model. +The model is trained with different learning rates and the best validation score achieved is 0.716119 for a learning rate of 3e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT) diff --git a/model_cards/Hate-speech-CNERG/dehatebert-mono-spanish/README.md b/model_cards/Hate-speech-CNERG/dehatebert-mono-spanish/README.md new file mode 100644 index 0000000000..b82b9ebf94 --- /dev/null +++ b/model_cards/Hate-speech-CNERG/dehatebert-mono-spanish/README.md @@ -0,0 +1,2 @@ +This model is used detecting **hatespeech** in **Spanish language**. The mono in the name refers to the monolingual setting, where the model is trained using only English language data. It is finetuned on multilingual bert model. +The model is trained with different learning rates and the best validation score achieved is 0.740287 for a learning rate of 3e-5. Training code can be found at this [url](https://github.com/punyajoy/DE-LIMIT)