Evaluating Sequence-to-Sequence Learning Models for If-Then Program Synthesis

TL;DR

This paper investigates the use of sequence-to-sequence models for automatically generating If-Then programs from natural language descriptions, aiming to simplify enterprise process automation for non-technical users.

Contribution

It demonstrates that Seq2Seq models are effective for synthesizing If-Then programs, showing promising results on real-world automation recipes.

Findings

Seq2Seq models perform well on Zapier recipes

Potential for applying models to complex program synthesis

Supports non-technical user automation creation

Abstract

Implementing enterprise process automation often requires significant technical expertise and engineering effort. It would be beneficial for non-technical users to be able to describe a business process in natural language and have an intelligent system generate the workflow that can be automatically executed. A building block of process automations are If-Then programs. In the consumer space, sites like IFTTT and Zapier allow users to create automations by defining If-Then programs using a graphical interface. We explore the efficacy of modeling If-Then programs as a sequence learning task. We find Seq2Seq approaches have high potential (performing strongly on the Zapier recipes) and can serve as a promising approach to more complex program synthesis challenges.