Generating computer code from natural language descriptions has been a long- standing problem. Prior work in this domain has restricted itself to generating code in one shot from a single description. To overcome this limitation, we propose a system that can engage users in a dialog to clarify their intent until it has all the information to produce correct code. To evaluate the efficacy of dialog in code generation, we focus on synthesizing conditional statements in the form of IFTTT recipes.

PDF

In Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP-17), pp. 175-180, Taipei, Taiwan, November 2017.

@inproceedings{chaurasia:ijcnlp17, title={Dialog for Language to Code}, author={Shobhit Chaurasia and Raymond J. Mooney}, booktitle={Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP-17)}, month={November}, address={Taipei, Taiwan}, pages={175-180}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127667", year={2017} }

Poster