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

arXiv: https://arxiv.org/abs/2002.03485 · HTML: https://mlsanity.com/paper/2002.03485/

## Key facts

- Cited by 3 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 10 Feb 2020.

## Built on by (most cited first, 3 of 3)

- [Reducing hallucination in structured outputs via Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.08189/) (2024)
- [SAGE: Smart home Agent with Grounded Execution](https://mlsanity.com/paper/2311.00772/) (2023)
- [Proactive Detection of Physical Inter-rule Vulnerabilities in IoT Services Using a Deep Learning Approach](https://mlsanity.com/paper/2406.03836/) (2024)

## Abstract (arXiv)

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.