first commit

Author: wasiahmad

.idea/.gitignore

@@ -0,0 +1,107 @@
+#### Files in this Repository
+
+```
+.
+├── LICENSE
+├── README.md
+├── codeXglue
+│   ├── code_to_code
+│   │   ├── CodeBLEU
+│   │   │   ├── bleu.py
+│   │   │   ├── calc_code_bleu.py
+│   │   │   ├── dataflow_match.py
+│   │   │   ├── keywords
+│   │   │   │   ├── c_sharp.txt
+│   │   │   │   ├── java.txt
+│   │   │   │   └── python.txt
+│   │   │   ├── parser
+│   │   │   │   ├── DFG.py
+│   │   │   │   ├── __init__.py
+│   │   │   │   ├── build.py
+│   │   │   │   ├── build.sh
+│   │   │   │   ├── my-languages.so
+│   │   │   │   └── utils.py
+│   │   │   ├── readme.txt
+│   │   │   ├── syntax_match.py
+│   │   │   ├── utils.py
+│   │   │   └── weighted_ngram_match.py
+│   │   ├── bleu.py
+│   │   ├── clone_detection
+│   │   │   ├── encode.py
+│   │   │   ├── eval.py
+│   │   │   ├── evaluator.py
+│   │   │   ├── prepare.sh
+│   │   │   └── run.sh
+│   │   ├── defect_prediction
+│   │   │   ├── encode.py
+│   │   │   ├── eval.py
+│   │   │   ├── evaluator.py
+│   │   │   ├── prepare.sh
+│   │   │   └── run.sh
+│   │   ├── encode.py
+│   │   ├── evaluator.py
+│   │   ├── refin_prep.sh
+│   │   ├── refin_run.sh
+│   │   ├── trans_prep.sh
+│   │   └── trans_run.sh
+│   ├── code_to_text
+│   │   ├── download.sh
+│   │   ├── encode.py
+│   │   ├── evaluator.py
+│   │   ├── generate.sh
+│   │   ├── multilingual.sh
+│   │   ├── prep.sh
+│   │   ├── python_tokenizer.py
+│   │   └── run.sh
+│   └── text_to_code
+│       ├── CodeBLEU
+│       │   ├── bleu.py
+│       │   ├── calc_code_bleu.py
+│       │   ├── dataflow_match.py
+│       │   ├── keywords
+│       │   │   ├── c_sharp.txt
+│       │   │   ├── java.txt
+│       │   │   └── python.txt
+│       │   ├── parser
+│       │   │   ├── DFG.py
+│       │   │   ├── __init__.py
+│       │   │   ├── build.py
+│       │   │   ├── build.sh
+│       │   │   ├── my-languages.so
+│       │   │   └── utils.py
+│       │   ├── readme.txt
+│       │   ├── syntax_match.py
+│       │   ├── utils.py
+│       │   └── weighted_ngram_match.py
+│       ├── bleu.py
+│       ├── encode.py
+│       ├── evaluator.py
+│       ├── generate.sh
+│       ├── prep.sh
+│       └── run.sh
+├── preprocessing
+│   ├── __init__.py
+│   ├── detokenize.py
+│   ├── preprocess.py
+│   ├── src
+│   │   ├── __init__.py
+│   │   ├── code_tokenizer.py
+│   │   ├── dataset.py
+│   │   ├── javalang_tokenizer.py
+│   │   ├── test_tokenize_cpp.py
+│   │   ├── test_tokenize_java.py
+│   │   ├── test_tokenize_python.py
+│   │   ├── timeout.py
+│   │   └── utils.py
+│   └── test_preprocess.py
+├── pretrain
+│   ├── absolute.sh
+│   └── binarize.sh
+├── requirements.txt
+├── sentencepiece
+│   ├── encode.py
+│   └── train.py
+├── setup.py
+└── stackoverflow
+    └── preprocess.py
+```

.idea/PLBART.iml

@@ -1,2 +1,42 @@
 # PLBART
-Code pre-release of our work, **Unified Pre-training for Program Understanding and Generation** accepted at NAACL 2021.
+Code pre-release of our work, [Unified Pre-training for Program Understanding and Generation]() accepted at NAACL 2021.
+
+#### Note. A detailed documentation is coming soon.
+
+### Pre-training data
+
+PLBART is pre-trained on Java and Python functions and natural language descriptions collected from Github and StackOverflow.
+
+
+### Evaluation tasks
+
+We evaluated PLBART on five tasks.
+
+- Code summarization [[info](https://github.com/microsoft/CodeXGLUE/tree/main/Code-Text/code-to-text#dataset)]
+- Code generation [[info](https://github.com/microsoft/CodeXGLUE/tree/main/Text-Code/text-to-code#task-definition)]
+- Code translation [[info](https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/code-to-code-trans#task-definition)]
+- Clone detection [[info](https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/Clone-detection-BigCloneBench#task-definition)]
+- Vulnerability detection [[info](https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/Defect-detection#codexglue----defect-detection)]
+
+
+### Notes
+
+- We will publish the pretrained PLBART checkpoint soon.
+- We list all the files in this repository [here](https://github.com/plbart-2020/PLBART/blob/main/FILEs.md).
+
+### Acknowledgement
+
+PLBART uses [Fairseq](https://github.com/pytorch/fairseq), [codeXglue](https://github.com/microsoft/CodeXGLUE), and [TransCoder](https://github.com/facebookresearch/TransCoder) and thanks the authors of these works for their contribution.
+
+
+### Citation
+
+```
+@inproceedings{ahmad2020summarization,
+    author = {Ahmad, Wasi Uddin and Chakraborty, Saikat and Ray, Baishakhi and Chang, Kai-Wei},
+    booktitle = {Proceedings of the 2021 Conference of the North {A}merican Chapter of the Association for Computational Linguistics},
+    title = {Unified Pre-training for Program Understanding and Generation},
+    year = {2021}
+}
+```
+