A Goal-Driven Natural Language Interface for Creating Application Integration Workflows

Web applications and services are increasingly important in a distributed internet filled with diverse cloud applications, each of which enable the completion narrowly defined tasks. Given explosion scale diversity such services, their composition integration for achieving complex user goals remains challenging task end-users requires lot development effort when specified by hand. We present demonstration Goal Oriented Flow Assistant (GOFA) system, provides natural language solution to generate workflows application integration. Our tool is built on three-step pipeline: it first uses Abstract Meaning Representation (AMR) parse utterances; then knowledge graph validate candidates; finally an AI planner compose candidate flow. provide video deployed system as part our submission.