@InProceedings{micelibarone-sennrich:2017:I17-2,
  author    = {Miceli Barone, Antonio Valerio  and  Sennrich, Rico},
  title     = {A Parallel Corpus of Python Functions and Documentation Strings for Automated Code Documentation and Code Generation},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {314--319},
  abstract  = {Automated documentation of programming source code and automated code
	generation from natural language are challenging tasks of both practical and
	scientific interest.
	Progress in these areas has been limited by the low availability of parallel
	corpora of code and natural language descriptions, which tend to be small and
	constrained to specific domains.
	In this work we introduce a large and diverse parallel corpus of a hundred
	thousands Python functions with their documentation strings ("docstrings")
	generated by scraping open source repositories on GitHub.
	We describe baseline results for the code documentation and code generation
	tasks obtained by neural machine translation.
	We also experiment with data augmentation techniques to further increase the
	amount of training data.
	We release our datasets and processing scripts in order to stimulate research
	in these areas.},
  url       = {http://www.aclweb.org/anthology/I17-2053}
}