stmnk commited on
Commit
e5e3262
·
1 Parent(s): 3aaf827

add article

Browse files
Files changed (1) hide show
  1. app.py +3 -5
app.py CHANGED
@@ -139,12 +139,10 @@ iface = gr.Interface(
139
  # gr.outputs.Textbox(label="Code Generated PL"))
140
  gr.outputs.Textbox(label="Docstring Generated (NL)"),
141
  title='Generate a documentation string for Python code',
142
- description='The application takes as input the python code for a function, or a class, and generates a documentation string, or code comment, for it using codeT5 fine tuned for code2text generation. Code to text generation, or code summarization, is a CodeXGLUE generation, or sequence to sequence, downstream task. CodeXGLUE stands for General Language Understanding Evaluation benchmark *for code*, which includes several datasets for diversified code intelligence downstream tasks.',
143
- article=r"""CodeXGLLUE task definition (and dataset):
144
-
145
- Code summarization (CodeSearchNet).
146
 
147
- A model is given the task to generate natural language comments for a code.
148
 
149
  For further details, see the [CodeXGLUE](https://github.com/microsoft/CodeXGLUE) benchmark dataset and open challenge for code intelligence.
150
  """,
 
139
  # gr.outputs.Textbox(label="Code Generated PL"))
140
  gr.outputs.Textbox(label="Docstring Generated (NL)"),
141
  title='Generate a documentation string for Python code',
142
+ description='The application takes as input the python code for a function, or a class, and generates a documentation string, or code comment, for it using codeT5 fine tuned for code2text generation. Code to text generation, or code summarization, is a CodeXGLUE generation, or sequence to sequence, downstream task. CodeXGLUE stands for General Language Understanding Evaluation benchmark *for code*, which includes diversified code intelligence downstream inference tasks and datasets.',
143
+ article=r"""CodeXGLLUE task definition (and dataset): *Code summarization (CodeSearchNet)*:
 
 
144
 
145
+ _A model is given the task to generate natural language comments for a programming language code input._
146
 
147
  For further details, see the [CodeXGLUE](https://github.com/microsoft/CodeXGLUE) benchmark dataset and open challenge for code intelligence.
148
  """,