Natural Language Sentence Generation from API Specifications
This addresses the accessibility gap for business users needing automation but lacking technical skills, though it appears incremental as it builds on existing chatbot and deep learning methods.
The paper tackles the problem of making APIs accessible to non-technical business users by generating sentences to train intent recognition models for chatbots, showing promising results in evaluation.
APIs are everywhere; they provide access to automation solutions that could help businesses automate some of their tasks. Unfortunately, they may not be accessible to the business users who need them but are not equipped with the necessary technical skills to leverage them. Wrapping these APIs with chatbot capabilities is one solution to make these automation solutions interactive. In this work, we propose a system to generate sentences to train intent recognition models, a crucial component within chatbots to understand natural language utterances from users. Evaluation of our approach based on deep learning models showed promising and inspiring results, and the human-in-the-loop interaction will provide further improvement on the system.