Skip to yearly menu bar Skip to main content


Latent Attention For If-Then Program Synthesis

Chang Liu · Xinyun Chen · Richard Shin · Mingcheng Chen · Dawn Song

Area 5+6+7+8 #50

Keywords: [ (Cognitive/Neuroscience) Language ] [ (Application) Natural Language and Text Processing ] [ Multi-task and Transfer Learning ] [ Deep Learning or Neural Networks ]


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 natural language structures that indicate the relevant parts for predicting program elements. Our architecture reduces the error rate by 28.57% compared to prior art. We also propose a one-shot learning scenario of If-Then program synthesis and simulate it with our existing dataset. We demonstrate a variation on the training procedure for this scenario that outperforms the original procedure, significantly closing the gap to the model trained with all data.

Live content is unavailable. Log in and register to view live content