From bf162ce8ca15fa0371cccb9ecf0d91404e39905f Mon Sep 17 00:00:00 2001 From: Ali Hamdi Ali Fadel Date: Wed, 21 Oct 2020 16:24:43 +0300 Subject: [PATCH] Add AI-SOCO models (#7867) --- .../ai-soco-c++-roberta-small-clas/README.md | 56 +++++++++++++++++++ .../ai-soco-c++-roberta-small/README.md | 55 ++++++++++++++++++ .../README.md | 56 +++++++++++++++++++ .../ai-soco-c++-roberta-tiny-96/README.md | 55 ++++++++++++++++++ .../ai-soco-c++-roberta-tiny-clas/README.md | 56 +++++++++++++++++++ .../aliosm/ai-soco-c++-roberta-tiny/README.md | 55 ++++++++++++++++++ 6 files changed, 333 insertions(+) create mode 100644 model_cards/aliosm/ai-soco-c++-roberta-small-clas/README.md create mode 100644 model_cards/aliosm/ai-soco-c++-roberta-small/README.md create mode 100644 model_cards/aliosm/ai-soco-c++-roberta-tiny-96-clas/README.md create mode 100644 model_cards/aliosm/ai-soco-c++-roberta-tiny-96/README.md create mode 100644 model_cards/aliosm/ai-soco-c++-roberta-tiny-clas/README.md create mode 100644 model_cards/aliosm/ai-soco-c++-roberta-tiny/README.md diff --git a/model_cards/aliosm/ai-soco-c++-roberta-small-clas/README.md b/model_cards/aliosm/ai-soco-c++-roberta-small-clas/README.md new file mode 100644 index 0000000000..f1bb39d776 --- /dev/null +++ b/model_cards/aliosm/ai-soco-c++-roberta-small-clas/README.md @@ -0,0 +1,56 @@ +--- +language: "c++" +tags: +- exbert +- authorship-identification +- fire2020 +- pan2020 +- ai-soco +- classification +license: "mit" +datasets: +- ai-soco +metrics: +- accuracy +--- + +# ai-soco-c++-roberta-small-clas + +## Model description + +`ai-soco-c++-roberta-small` model fine-tuned on [AI-SOCO](https://sites.google.com/view/ai-soco-2020) task. + +#### How to use + +You can use the model directly after tokenizing the text using the provided tokenizer with the model files. + +#### Limitations and bias + +The model is limited to C++ programming language only. + +## Training data + +The model initialized from [`ai-soco-c++-roberta-small`](https://github.com/huggingface/transformers/blob/master/model_cards/aliosm/ai-soco-c++-roberta-small) model and trained using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset to do text classification. + +## Training procedure + +The model trained on Google Colab platform using V100 GPU for 10 epochs, 32 batch size, 512 max sequence length (sequences larger than 512 were truncated). Each continues 4 spaces were converted to a single tab character (`\t`) before tokenization. + +## Eval results + +The model achieved 93.19%/92.88% accuracy on AI-SOCO task and ranked in the 4th place. + +### BibTeX entry and citation info + +```bibtex +@inproceedings{ai-soco-2020-fire, + title = "Overview of the {PAN@FIRE} 2020 Task on {Authorship Identification of SOurce COde (AI-SOCO)}", + author = "Fadel, Ali and Musleh, Husam and Tuffaha, Ibraheem and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Rosso, Paolo", + booktitle = "Proceedings of The 12th meeting of the Forum for Information Retrieval Evaluation (FIRE 2020)", + year = "2020" +} +``` + + + + diff --git a/model_cards/aliosm/ai-soco-c++-roberta-small/README.md b/model_cards/aliosm/ai-soco-c++-roberta-small/README.md new file mode 100644 index 0000000000..7272351fd8 --- /dev/null +++ b/model_cards/aliosm/ai-soco-c++-roberta-small/README.md @@ -0,0 +1,55 @@ +--- +language: "c++" +tags: +- exbert +- authorship-identification +- fire2020 +- pan2020 +- ai-soco +license: "mit" +datasets: +- ai-soco +metrics: +- perplexity +--- + +# ai-soco-c++-roberta-small + +## Model description + +From scratch pre-trained RoBERTa model with 6 layers and 12 attention heads using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset which consists of C++ codes crawled from CodeForces website. + +## Intended uses & limitations + +The model can be used to do code classification, authorship identification and other downstream tasks on C++ programming language. + +#### How to use + +You can use the model directly after tokenizing the text using the provided tokenizer with the model files. + +#### Limitations and bias + +The model is limited to C++ programming language only. + +## Training data + +The model initialized randomly and trained using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset which contains 100K C++ source codes. + +## Training procedure + +The model trained on Google Colab platform with 8 TPU cores for 200 epochs, 16\*8 batch size, 512 max sequence length and MLM objective. Other parameters were defaulted to the values mentioned in [`run_language_modelling.py`](https://github.com/huggingface/transformers/blob/master/examples/language-modeling/run_language_modeling.py) script. Each continues 4 spaces were converted to a single tab character (`\t`) before tokenization. + +### BibTeX entry and citation info + +```bibtex +@inproceedings{ai-soco-2020-fire, + title = "Overview of the {PAN@FIRE} 2020 Task on {Authorship Identification of SOurce COde (AI-SOCO)}", + author = "Fadel, Ali and Musleh, Husam and Tuffaha, Ibraheem and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Rosso, Paolo", + booktitle = "Proceedings of The 12th meeting of the Forum for Information Retrieval Evaluation (FIRE 2020)", + year = "2020" +} +``` + + + + diff --git a/model_cards/aliosm/ai-soco-c++-roberta-tiny-96-clas/README.md b/model_cards/aliosm/ai-soco-c++-roberta-tiny-96-clas/README.md new file mode 100644 index 0000000000..88bb496da8 --- /dev/null +++ b/model_cards/aliosm/ai-soco-c++-roberta-tiny-96-clas/README.md @@ -0,0 +1,56 @@ +--- +language: "c++" +tags: +- exbert +- authorship-identification +- fire2020 +- pan2020 +- ai-soco +- classification +license: "mit" +datasets: +- ai-soco +metrics: +- accuracy +--- + +# ai-soco-c++-roberta-tiny-96-clas + +## Model description + +`ai-soco-c++-roberta-tiny-96` model fine-tuned on [AI-SOCO](https://sites.google.com/view/ai-soco-2020) task. + +#### How to use + +You can use the model directly after tokenizing the text using the provided tokenizer with the model files. + +#### Limitations and bias + +The model is limited to C++ programming language only. + +## Training data + +The model initialized from [`ai-soco-c++-roberta-tiny-96`](https://github.com/huggingface/transformers/blob/master/model_cards/aliosm/ai-soco-c++-roberta-tiny-96) model and trained using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset to do text classification. + +## Training procedure + +The model trained on Google Colab platform using V100 GPU for 10 epochs, 16 batch size, 512 max sequence length (sequences larger than 512 were truncated). Each continues 4 spaces were converted to a single tab character (`\t`) before tokenization. + +## Eval results + +The model achieved 91.12%/91.02% accuracy on AI-SOCO task and ranked in the 7th place. + +### BibTeX entry and citation info + +```bibtex +@inproceedings{ai-soco-2020-fire, + title = "Overview of the {PAN@FIRE} 2020 Task on {Authorship Identification of SOurce COde (AI-SOCO)}", + author = "Fadel, Ali and Musleh, Husam and Tuffaha, Ibraheem and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Rosso, Paolo", + booktitle = "Proceedings of The 12th meeting of the Forum for Information Retrieval Evaluation (FIRE 2020)", + year = "2020" +} +``` + + + + diff --git a/model_cards/aliosm/ai-soco-c++-roberta-tiny-96/README.md b/model_cards/aliosm/ai-soco-c++-roberta-tiny-96/README.md new file mode 100644 index 0000000000..ea6fad87f0 --- /dev/null +++ b/model_cards/aliosm/ai-soco-c++-roberta-tiny-96/README.md @@ -0,0 +1,55 @@ +--- +language: "c++" +tags: +- exbert +- authorship-identification +- fire2020 +- pan2020 +- ai-soco +license: "mit" +datasets: +- ai-soco +metrics: +- perplexity +--- + +# ai-soco-c++-roberta-tiny-96 + +## Model description + +From scratch pre-trained RoBERTa model with 1 layers and 96 attention heads using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset which consists of C++ codes crawled from CodeForces website. + +## Intended uses & limitations + +The model can be used to do code classification, authorship identification and other downstream tasks on C++ programming language. + +#### How to use + +You can use the model directly after tokenizing the text using the provided tokenizer with the model files. + +#### Limitations and bias + +The model is limited to C++ programming language only. + +## Training data + +The model initialized randomly and trained using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset which contains 100K C++ source codes. + +## Training procedure + +The model trained on Google Colab platform with 8 TPU cores for 200 epochs, 16\*8 batch size, 512 max sequence length and MLM objective. Other parameters were defaulted to the values mentioned in [`run_language_modelling.py`](https://github.com/huggingface/transformers/blob/master/examples/language-modeling/run_language_modeling.py) script. Each continues 4 spaces were converted to a single tab character (`\t`) before tokenization. + +### BibTeX entry and citation info + +```bibtex +@inproceedings{ai-soco-2020-fire, + title = "Overview of the {PAN@FIRE} 2020 Task on {Authorship Identification of SOurce COde (AI-SOCO)}", + author = "Fadel, Ali and Musleh, Husam and Tuffaha, Ibraheem and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Rosso, Paolo", + booktitle = "Proceedings of The 12th meeting of the Forum for Information Retrieval Evaluation (FIRE 2020)", + year = "2020" +} +``` + + + + diff --git a/model_cards/aliosm/ai-soco-c++-roberta-tiny-clas/README.md b/model_cards/aliosm/ai-soco-c++-roberta-tiny-clas/README.md new file mode 100644 index 0000000000..d2bf508248 --- /dev/null +++ b/model_cards/aliosm/ai-soco-c++-roberta-tiny-clas/README.md @@ -0,0 +1,56 @@ +--- +language: "c++" +tags: +- exbert +- authorship-identification +- fire2020 +- pan2020 +- ai-soco +- classification +license: "mit" +datasets: +- ai-soco +metrics: +- accuracy +--- + +# ai-soco-c++-roberta-tiny-clas + +## Model description + +`ai-soco-c++-roberta-tiny` model fine-tuned on [AI-SOCO](https://sites.google.com/view/ai-soco-2020) task. + +#### How to use + +You can use the model directly after tokenizing the text using the provided tokenizer with the model files. + +#### Limitations and bias + +The model is limited to C++ programming language only. + +## Training data + +The model initialized from [`ai-soco-c++-roberta-tiny`](https://github.com/huggingface/transformers/blob/master/model_cards/aliosm/ai-soco-c++-roberta-tiny) model and trained using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset to do text classification. + +## Training procedure + +The model trained on Google Colab platform using V100 GPU for 10 epochs, 32 batch size, 512 max sequence length (sequences larger than 512 were truncated). Each continues 4 spaces were converted to a single tab character (`\t`) before tokenization. + +## Eval results + +The model achieved 87.66%/87.46% accuracy on AI-SOCO task and ranked in the 9th place. + +### BibTeX entry and citation info + +```bibtex +@inproceedings{ai-soco-2020-fire, + title = "Overview of the {PAN@FIRE} 2020 Task on {Authorship Identification of SOurce COde (AI-SOCO)}", + author = "Fadel, Ali and Musleh, Husam and Tuffaha, Ibraheem and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Rosso, Paolo", + booktitle = "Proceedings of The 12th meeting of the Forum for Information Retrieval Evaluation (FIRE 2020)", + year = "2020" +} +``` + + + + diff --git a/model_cards/aliosm/ai-soco-c++-roberta-tiny/README.md b/model_cards/aliosm/ai-soco-c++-roberta-tiny/README.md new file mode 100644 index 0000000000..2c54c593b8 --- /dev/null +++ b/model_cards/aliosm/ai-soco-c++-roberta-tiny/README.md @@ -0,0 +1,55 @@ +--- +language: "c++" +tags: +- exbert +- authorship-identification +- fire2020 +- pan2020 +- ai-soco +license: "mit" +datasets: +- ai-soco +metrics: +- perplexity +--- + +# ai-soco-c++-roberta-tiny + +## Model description + +From scratch pre-trained RoBERTa model with 1 layers and 12 attention heads using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset which consists of C++ codes crawled from CodeForces website. + +## Intended uses & limitations + +The model can be used to do code classification, authorship identification and other downstream tasks on C++ programming language. + +#### How to use + +You can use the model directly after tokenizing the text using the provided tokenizer with the model files. + +#### Limitations and bias + +The model is limited to C++ programming language only. + +## Training data + +The model initialized randomly and trained using [AI-SOCO](https://sites.google.com/view/ai-soco-2020) dataset which contains 100K C++ source codes. + +## Training procedure + +The model trained on Google Colab platform with 8 TPU cores for 200 epochs, 32\*8 batch size, 512 max sequence length and MLM objective. Other parameters were defaulted to the values mentioned in [`run_language_modelling.py`](https://github.com/huggingface/transformers/blob/master/examples/language-modeling/run_language_modeling.py) script. Each continues 4 spaces were converted to a single tab character (`\t`) before tokenization. + +### BibTeX entry and citation info + +```bibtex +@inproceedings{ai-soco-2020-fire, + title = "Overview of the {PAN@FIRE} 2020 Task on {Authorship Identification of SOurce COde (AI-SOCO)}", + author = "Fadel, Ali and Musleh, Husam and Tuffaha, Ibraheem and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Rosso, Paolo", + booktitle = "Proceedings of The 12th meeting of the Forum for Information Retrieval Evaluation (FIRE 2020)", + year = "2020" +} +``` + + + +