Trigger Action Programs (TAPs) are event-driven rules that allow users to automate smart-devices and internet services. Users can write TAPs by specifying triggers and actions from a set of predefined channels and functions. Despite its simplicity, composing TAPs can still be challenging for users due to the enormous search space of available triggers and actions. The growing popularity of TAPs is followed by the increasing number of supported devices and services, resulting in a huge number of possible combinations between triggers and actions. Motivated by such a fact, we improve our prior work and propose \textit{RecipeGen++}, a deep-learning-based approach that leverages Transformer seq2seq (sequence-to-sequence) architecture to generate TAPs given natural language descriptions. \textit{RecipeGen++} can generate TAPs in the \textit{Interactive}, \textit{One-Click}, or \textit{Functionality Discovery} modes. In the Interactive mode, users can provide feedback to guide the prediction of a trigger or action component. In contrast, the One-Click mode allows users to generate all TAP components directly. Additionally, \textit{RecipeGen++} also enables users to discover functionalities at the channel level through the Functionality Discovery mode. We have evaluated \textit{RecipeGen++} on real-world datasets in all modes. Our results demonstrate that \textit{RecipeGen++} can outperform the baseline by 2.2%-16.2% in the gold-standard benchmark and 5%-29.2% in the noisy benchmark.

Demo: https://4ek5.short.gy/RecipeGen

Tool: https://huggingface.co/spaces/imamnurby/RecipeGen

GitHub: https://github.com/imamnurby/RecipeGen