Project Logo

About Tellina

Star Fork Issue

Tellina automatically translates the natural language commands of end-user programmers into a programming language. Currently Tellina supports Bash as its target language.

Source Code & Data

The source code for this website and the machine learning model & data is available on Github.

Publications

The following papers describe the research work and technical details of Tellina.

If you use Tellina in your work, please cite the relevant paper(s) accordingly.

Program Synthesis from Natural Language Using Recurrent Neural Networks. UW-CSE-TR. 2017
Keywords: stage-wise translation, user study
@techreport{LinWPVZE2017:TR, 
  author = {Xi Victoria Lin and Chenglong Wang and Deric Pang and Kevin Vu and Luke Zettlemoyer and Michael D. Ernst}, 
  title = {Program synthesis from natural language using recurrent neural networks}, 
  institution = {University of Washington Department of Computer Science and Engineering}, 
  number = {UW-CSE-17-03-01}, 
  address = {Seattle, WA, USA}, 
  month = mar, 
  year = {2017} 
}
NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System. LREC 2018.
Keywords: end-to-end translation, CopyNet, sub-token, 100 Bash utilities, dataset
@inproceedings{LinWZE2018:NL2Bash, 
  author = {Xi Victoria Lin and Chenglong Wang and Luke Zettlemoyer and Michael D. Ernst}, 
  title = {NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System}, 
  booktitle = {Proceedings of the Eleventh International Conference on Language Resources
               and Evaluation {LREC} 2018, Miyazaki (Japan), 7-12 May, 2018.},
  year = {2018} 
}

Team

Tellina is written by Victoria Lin, with help from Chenglong Wang and Deric Pang.
Research advisors: Michael D. Ernst and Luke Zettlemoyer.
* We thank the Bash programmers who worked with us on data collection. You brought Tellina to life!