Many texts, especially in Chemistry and Biol-ogy, describe complex processes. To answer questions about such processes one needs to understand the interactions between the different entities and to track the state transition between the different stages of the process. In this work, we tackle this problem by learning to generate corresponding code to a text that describes a chemical reaction process and a question that asks about the process outcome in a different setup. We define a domain-specific-language for such processes, and contribute to the community a unique dataset, curated by chemists, of process texts, simulation questions, and their corresponding codes. We propose a reinforcement-learning based approach to learn to generate code based on texts and questions optimizing both for syntactic code similarity and the semantic run-time similarity.
