• Computer Science
  • Published in NIPS 2016

Latent Attention For If-Then Program Synthesis

@inproceedings{Chen2016LatentAF,
  title={Latent Attention For If-Then Program Synthesis},
  author={Xinyun Chen and Chang Liu and Richard Shin and Dawn Xiaodong Song},
  booktitle={NIPS},
  year={2016}
}
Automatic translation from natural language descriptions into programs is a long-standing challenging problem. In this work, we consider a simple yet important sub-problem: translation from textual descriptions to If-Then programs. We devise a novel neural network architecture for this task which we train end-to-end. Specifically, we introduce Latent Attention, which computes multiplicative weights for the words in the description in a two-stage process with the goal of better leveraging the… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 27 CITATIONS

Dialog for Language to Code

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

AutoTap: Synthesizing and Repairing Trigger-Action Programs Using LTL Properties

  • 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE)
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND & METHODS

Bidirectional Attention for SQL Generation

  • 2019 IEEE 4th International Conference on Cloud Computing and Big Data Analysis (ICCCBDA)
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND